diff options
Diffstat (limited to 'include/linux')
138 files changed, 2011 insertions, 939 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a70e62d69dc7..3f2e93ed9730 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1094,6 +1094,17 @@ static inline acpi_handle acpi_get_processor_handle(int cpu) #endif /* !CONFIG_ACPI */ +#ifdef CONFIG_ACPI_HMAT +int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid, + resource_size_t *size); +#else +static inline int hmat_get_extended_linear_cache_size(struct resource *backing_res, + int nid, resource_size_t *size) +{ + return -EOPNOTSUPP; +} +#endif + extern void arch_post_acpi_subsys_init(void); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h index bbc4730a6505..c0989b5b0407 100644 --- a/include/linux/bit_spinlock.h +++ b/include/linux/bit_spinlock.h @@ -13,7 +13,7 @@ * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ -static inline void bit_spin_lock(int bitnum, unsigned long *addr) +static __always_inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters @@ -38,7 +38,7 @@ static inline void bit_spin_lock(int bitnum, unsigned long *addr) /* * Return true if it was acquired */ -static inline int bit_spin_trylock(int bitnum, unsigned long *addr) +static __always_inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) @@ -54,7 +54,7 @@ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) /* * bit-based spin_unlock() */ -static inline void bit_spin_unlock(int bitnum, unsigned long *addr) +static __always_inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); @@ -71,7 +71,7 @@ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ -static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) +static __always_inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index d8a8d245824a..4c506e76a808 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -18,6 +18,8 @@ enum bootmem_type { #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void __init register_page_bootmem_info_node(struct pglist_data *pgdat); +void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, + unsigned long nr_pages); void get_page_bootmem(unsigned long info, struct page *page, enum bootmem_type type); @@ -58,6 +60,11 @@ static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } +static inline void register_page_bootmem_memmap(unsigned long section_nr, + struct page *map, unsigned long nr_pages) +{ +} + static inline void put_page_bootmem(struct page *page) { } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index fab70b26e131..f0a4ad7839b6 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -270,7 +270,7 @@ int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct folio **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); -void block_commit_write(struct page *page, unsigned int from, unsigned int to); +void block_commit_write(struct folio *folio, size_t from, size_t to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ba8f52d48b94..204b22a99c4b 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -184,6 +184,12 @@ static inline void bvec_iter_advance_single(const struct bio_vec *bv, ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len)) +#define for_each_mp_bvec(bvl, bio_vec, iter, start) \ + for (iter = (start); \ + (iter).bi_size && \ + ((bvl = mp_bvec_iter_bvec((bio_vec), (iter))), 1); \ + bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len)) + /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 485b651869d9..5bc8f55c8cca 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -710,6 +710,7 @@ struct cgroup_subsys { void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_killed)(struct cgroup_subsys_state *css); void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu); int (*css_extra_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 28e999f2c642..e7da3c3b098b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -344,7 +344,7 @@ static inline u64 cgroup_id(const struct cgroup *cgrp) */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { - return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); + return css->flags & CSS_DYING; } static inline void cgroup_get(struct cgroup *cgrp) diff --git a/include/linux/cma.h b/include/linux/cma.h index d15b64f51336..62d9c1cf6326 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -40,6 +40,9 @@ static inline int __init cma_declare_contiguous(phys_addr_t base, return cma_declare_contiguous_nid(base, size, limit, alignment, order_per_bit, fixed, name, res_cma, NUMA_NO_NODE); } +extern int __init cma_declare_contiguous_multi(phys_addr_t size, + phys_addr_t align, unsigned int order_per_bit, + const char *name, struct cma **res_cma, int nid); extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, const char *name, @@ -50,12 +53,14 @@ extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); +extern bool cma_intersects(struct cma *cma, unsigned long start, unsigned long end); extern void cma_reserve_pages_on_error(struct cma *cma); #ifdef CONFIG_CMA struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp); bool cma_free_folio(struct cma *cma, const struct folio *folio); +bool cma_validate_zones(struct cma *cma); #else static inline struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp) { @@ -66,6 +71,10 @@ static inline bool cma_free_folio(struct cma *cma, const struct folio *folio) { return false; } +static inline bool cma_validate_zones(struct cma *cma) +{ + return false; +} #endif #endif diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 7bf0c521db63..173d9c07a895 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -95,7 +95,7 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern bool compaction_suitable(struct zone *zone, int order, - int highest_zoneidx); + unsigned long watermark, int highest_zoneidx); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); @@ -113,7 +113,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) } static inline bool compaction_suitable(struct zone *zone, int order, - int highest_zoneidx) + unsigned long watermark, + int highest_zoneidx) { return false; } diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 2e7c2c282f3a..4fc8e26914ad 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -128,3 +128,11 @@ */ #define ASM_INPUT_G "ir" #define ASM_INPUT_RM "r" + +/* + * Declare compiler support for __typeof_unqual__() operator. + * + * Bindgen uses LLVM even if our C compiler is GCC, so we cannot + * rely on the auto-detected CONFIG_CC_HAS_TYPEOF_UNQUAL. + */ +#define CC_HAS_TYPEOF_UNQUAL (__clang_major__ >= 19) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c9b58188ec61..32048052c64a 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -137,3 +137,11 @@ #if GCC_VERSION < 90100 #undef __alloc_size__ #endif + +/* + * Declare compiler support for __typeof_unqual__() operator. + * + * Bindgen uses LLVM even if our C compiler is GCC, so we cannot + * rely on the auto-detected CONFIG_CC_HAS_TYPEOF_UNQUAL. + */ +#define CC_HAS_TYPEOF_UNQUAL (__GNUC__ >= 14) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 9fc30b6b80c9..27725f1ab5ab 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -226,6 +226,26 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __BUILD_BUG_ON_ZERO_MSG(!__is_noncstr(p), \ "must be non-C-string (not NUL-terminated)") +/* + * Use __typeof_unqual__() when available. + * + * XXX: Remove test for __CHECKER__ once + * sparse learns about __typeof_unqual__(). + */ +#if CC_HAS_TYPEOF_UNQUAL && !defined(__CHECKER__) +# define USE_TYPEOF_UNQUAL 1 +#endif + +/* + * Define TYPEOF_UNQUAL() to use __typeof_unqual__() as typeof + * operator when available, to return an unqualified type of the exp. + */ +#if defined(USE_TYPEOF_UNQUAL) +# define TYPEOF_UNQUAL(exp) __typeof_unqual__(exp) +#else +# define TYPEOF_UNQUAL(exp) __typeof__(exp) +#endif + #endif /* __KERNEL__ */ #if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e09d323be845..501cffddc2f4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -57,7 +57,7 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __user BTF_TYPE_TAG(user) # endif # define __iomem -# define __percpu BTF_TYPE_TAG(percpu) +# define __percpu __percpu_qual BTF_TYPE_TAG(percpu) # define __rcu BTF_TYPE_TAG(rcu) # define __chk_user_ptr(x) (void)0 diff --git a/include/linux/context_tracking_irq.h b/include/linux/context_tracking_irq.h index c50b5670c4a5..197916ee91a4 100644 --- a/include/linux/context_tracking_irq.h +++ b/include/linux/context_tracking_irq.h @@ -10,12 +10,12 @@ void ct_irq_exit_irqson(void); void ct_nmi_enter(void); void ct_nmi_exit(void); #else -static inline void ct_irq_enter(void) { } -static inline void ct_irq_exit(void) { } +static __always_inline void ct_irq_enter(void) { } +static __always_inline void ct_irq_exit(void) { } static inline void ct_irq_enter_irqson(void) { } static inline void ct_irq_exit_irqson(void) { } -static inline void ct_nmi_enter(void) { } -static inline void ct_nmi_exit(void) { } +static __always_inline void ct_nmi_enter(void) { } +static __always_inline void ct_nmi_exit(void) { } #endif #endif diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 17276965ff1d..d79a242b271d 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -71,7 +71,8 @@ enum coresight_dev_subtype_source { enum coresight_dev_subtype_helper { CORESIGHT_DEV_SUBTYPE_HELPER_CATU, - CORESIGHT_DEV_SUBTYPE_HELPER_ECT_CTI + CORESIGHT_DEV_SUBTYPE_HELPER_ECT_CTI, + CORESIGHT_DEV_SUBTYPE_HELPER_CTCU, }; /** @@ -238,7 +239,7 @@ struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); atomic_t __percpu *cpu_map; atomic_t perf_cs_etm_session_active; - spinlock_t lock; + raw_spinlock_t lock; }; /** @@ -301,7 +302,7 @@ struct coresight_device { /* system configuration and feature lists */ struct list_head feature_csdev_list; struct list_head config_csdev_list; - spinlock_t cscfg_csdev_lock; + raw_spinlock_t cscfg_csdev_lock; void *active_cscfg_ctxt; }; @@ -329,17 +330,29 @@ static struct coresight_dev_list (var) = { \ #define to_coresight_device(d) container_of(d, struct coresight_device, dev) +/** + * struct coresight_path - data needed by enable/disable path + * @path_list: path from source to sink. + * @trace_id: trace_id of the whole path. + */ +struct coresight_path { + struct list_head path_list; + u8 trace_id; +}; + enum cs_mode { CS_MODE_DISABLED, CS_MODE_SYSFS, CS_MODE_PERF, }; +#define coresight_ops(csdev) csdev->ops #define source_ops(csdev) csdev->ops->source_ops #define sink_ops(csdev) csdev->ops->sink_ops #define link_ops(csdev) csdev->ops->link_ops #define helper_ops(csdev) csdev->ops->helper_ops #define ect_ops(csdev) csdev->ops->ect_ops +#define panic_ops(csdev) csdev->ops->panic_ops /** * struct coresight_ops_sink - basic operations for a sink @@ -389,7 +402,7 @@ struct coresight_ops_link { struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode, struct coresight_trace_id_map *id_map); + enum cs_mode mode, struct coresight_path *path); void (*disable)(struct coresight_device *csdev, struct perf_event *event); }; @@ -409,11 +422,24 @@ struct coresight_ops_helper { int (*disable)(struct coresight_device *csdev, void *data); }; + +/** + * struct coresight_ops_panic - Generic device ops for panic handing + * + * @sync : Sync the device register state/trace data + */ +struct coresight_ops_panic { + int (*sync)(struct coresight_device *csdev); +}; + struct coresight_ops { + int (*trace_id)(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_device *sink); const struct coresight_ops_sink *sink_ops; const struct coresight_ops_link *link_ops; const struct coresight_ops_source *source_ops; const struct coresight_ops_helper *helper_ops; + const struct coresight_ops_panic *panic_ops; }; static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa, @@ -459,8 +485,11 @@ static inline struct clk *coresight_get_enable_apb_pclk(struct device *dev) int ret; pclk = clk_get(dev, "apb_pclk"); - if (IS_ERR(pclk)) - return NULL; + if (IS_ERR(pclk)) { + pclk = clk_get(dev, "apb"); + if (IS_ERR(pclk)) + return NULL; + } ret = clk_prepare_enable(pclk); if (ret) { @@ -649,6 +678,10 @@ extern int coresight_enable_sysfs(struct coresight_device *csdev); extern void coresight_disable_sysfs(struct coresight_device *csdev); extern int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value); +typedef void (*coresight_timeout_cb_t) (struct csdev_access *, u32, int, int); +extern int coresight_timeout_action(struct csdev_access *csa, u32 offset, + int position, int value, + coresight_timeout_cb_t cb); extern int coresight_claim_device(struct coresight_device *csdev); extern int coresight_claim_device_unlocked(struct coresight_device *csdev); @@ -694,4 +727,6 @@ int coresight_init_driver(const char *drv, struct amba_driver *amba_drv, void coresight_remove_driver(struct amba_driver *amba_drv, struct platform_driver *pdev_drv); +int coresight_etm_get_trace_id(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_device *sink); #endif /* _LINUX_COREISGHT_H */ diff --git a/include/linux/counter.h b/include/linux/counter.h index 426b7d58a438..f208e867dd0f 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -580,6 +580,9 @@ struct counter_array { #define COUNTER_COMP_CEILING(_read, _write) \ COUNTER_COMP_COUNT_U64("ceiling", _read, _write) +#define COUNTER_COMP_COMPARE(_read, _write) \ + COUNTER_COMP_COUNT_U64("compare", _read, _write) + #define COUNTER_COMP_COUNT_MODE(_read, _write, _available) \ { \ .type = COUNTER_COMP_COUNT_MODE, \ diff --git a/include/linux/cper.h b/include/linux/cper.h index 265b0f8fc0b3..0ed60a91eca9 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -89,6 +89,10 @@ enum { #define CPER_NOTIFY_DMAR \ GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ 0x72, 0x2D, 0xEB, 0x41) +/* CXL Protocol Error Section */ +#define CPER_SEC_CXL_PROT_ERR \ + GUID_INIT(0x80B9EFB4, 0x52B5, 0x4DE3, 0xA7, 0x77, 0x68, 0x78, \ + 0x4B, 0x77, 0x10, 0x48) /* CXL Event record UUIDs are formatted as GUIDs and reported in section type */ /* @@ -601,4 +605,8 @@ void cper_estatus_print(const char *pfx, int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); int cper_estatus_check(const struct acpi_hest_generic_status *estatus); +struct cxl_cper_sec_prot_err; +void cxl_cper_print_prot_err(const char *pfx, + const struct cxl_cper_sec_prot_err *prot_err); + #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6a0a8f1c7c90..e3049543008b 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -148,7 +148,7 @@ static inline int suspend_disable_secondary_cpus(void) } static inline void suspend_enable_secondary_cpus(void) { - return thaw_secondary_cpus(); + thaw_secondary_cpus(); } #else /* !CONFIG_PM_SLEEP_SMP */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6cc5e484547c..1987400000b4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -116,7 +116,6 @@ enum cpuhp_state { CPUHP_NET_IUCV_PREPARE, CPUHP_ARM_BL_PREPARE, CPUHP_TRACE_RB_PREPARE, - CPUHP_MM_ZS_PREPARE, CPUHP_MM_ZSWP_POOL_PREPARE, CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_ZCOMP_PREPARE, diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index 5a9df944fb80..1fe7e7d1b214 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -32,13 +32,12 @@ int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, #define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() #endif -void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high); +void __init reserve_crashkernel_generic(unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high); #else -static inline void __init reserve_crashkernel_generic(char *cmdline, +static inline void __init reserve_crashkernel_generic( unsigned long long crash_size, unsigned long long crash_base, unsigned long long crash_low_size, diff --git a/include/linux/damon.h b/include/linux/damon.h index c9074d569596..47e36e6ea203 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -36,6 +36,16 @@ struct damon_addr_range { }; /** + * struct damon_size_range - Represents size for filter to operate on [@min, @max]. + * @min: Min size (inclusive). + * @max: Max size (inclusive). + */ +struct damon_size_range { + unsigned long min; + unsigned long max; +}; + +/** * struct damon_region - Represents a monitoring target region. * @ar: The address range of the region. * @sampling_addr: Address of the sample for the next access check. @@ -324,8 +334,11 @@ struct damos_stat { /** * enum damos_filter_type - Type of memory for &struct damos_filter * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. + * @DAMOS_FILTER_TYPE_ACTIVE: Active pages. * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. * @DAMOS_FILTER_TYPE_YOUNG: Recently accessed pages. + * @DAMOS_FILTER_TYPE_HUGEPAGE_SIZE: Page is part of a hugepage. + * @DAMOS_FILTER_TYPE_UNMAPPED: Unmapped pages. * @DAMOS_FILTER_TYPE_ADDR: Address range. * @DAMOS_FILTER_TYPE_TARGET: Data Access Monitoring target. * @NR_DAMOS_FILTER_TYPES: Number of filter types. @@ -343,8 +356,11 @@ struct damos_stat { */ enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, + DAMOS_FILTER_TYPE_ACTIVE, DAMOS_FILTER_TYPE_MEMCG, DAMOS_FILTER_TYPE_YOUNG, + DAMOS_FILTER_TYPE_HUGEPAGE_SIZE, + DAMOS_FILTER_TYPE_UNMAPPED, DAMOS_FILTER_TYPE_ADDR, DAMOS_FILTER_TYPE_TARGET, NR_DAMOS_FILTER_TYPES, @@ -360,6 +376,7 @@ enum damos_filter_type { * @target_idx: Index of the &struct damon_target of * &damon_ctx->adaptive_targets if @type is * DAMOS_FILTER_TYPE_TARGET. + * @sz_range: Size range if @type is DAMOS_FILTER_TYPE_HUGEPAGE_SIZE. * @list: List head for siblings. * * Before applying the &damos->action to a memory region, DAMOS checks if each @@ -376,6 +393,7 @@ struct damos_filter { unsigned short memcg_id; struct damon_addr_range addr_range; int target_idx; + struct damon_size_range sz_range; }; struct list_head list; }; @@ -432,6 +450,8 @@ struct damos_access_pattern { * @wmarks: Watermarks for automated (in)activation of this scheme. * @target_nid: Destination node if @action is "migrate_{hot,cold}". * @filters: Additional set of &struct damos_filter for &action. + * @ops_filters: ops layer handling &struct damos_filter objects list. + * @last_applied: Last @action applied ops-managing entity. * @stat: Statistics of this scheme. * @list: List head for siblings. * @@ -454,6 +474,15 @@ struct damos_access_pattern { * implementation could check pages of the region and skip &action to respect * &filters * + * The minimum entity that @action can be applied depends on the underlying + * &struct damon_operations. Since it may not be aligned with the core layer + * abstract, namely &struct damon_region, &struct damon_operations could apply + * @action to same entity multiple times. Large folios that underlying on + * multiple &struct damon region objects could be such examples. The &struct + * damon_operations can use @last_applied to avoid that. DAMOS core logic + * unsets @last_applied when each regions walking for applying the scheme is + * finished. + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -475,6 +504,9 @@ struct damos { * layer-handled filters. If true, operations layer allows it, too. */ bool core_filters_allowed; + /* whether to reject core/ops filters umatched regions */ + bool core_filters_default_reject; + bool ops_filters_default_reject; /* public: */ struct damos_quota quota; struct damos_watermarks wmarks; @@ -482,6 +514,8 @@ struct damos { int target_nid; }; struct list_head filters; + struct list_head ops_filters; + void *last_applied; struct damos_stat stat; struct list_head list; }; @@ -510,7 +544,6 @@ enum damon_ops_id { * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. - * @reset_aggregated: Reset aggregated accesses monitoring results. * @get_scheme_score: Get the score of a region for a scheme. * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. @@ -522,8 +555,7 @@ enum damon_ops_id { * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting * the monitoring, @update after each &damon_attrs.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each - * &damon_attrs.sample_interval. Finally, @reset_aggregated is called after - * each &damon_attrs.aggr_interval. + * &damon_attrs.sample_interval. * * Each &struct damon_operations instance having valid @id can be registered * via damon_register_ops() and selected by damon_select_ops() later. @@ -538,8 +570,6 @@ enum damon_ops_id { * last preparation and update the number of observed accesses of each region. * It should also return max number of observed accesses that made as a result * of its update. The value will be used for regions adjustment threshold. - * @reset_aggregated should reset the access monitoring results that aggregated - * by @check_accesses. * @get_scheme_score should return the priority score of a region for a scheme * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided @@ -557,7 +587,6 @@ struct damon_operations { void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); - void (*reset_aggregated)(struct damon_ctx *context); int (*get_scheme_score)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); @@ -571,43 +600,28 @@ struct damon_operations { /** * struct damon_callback - Monitoring events notification callbacks. * - * @before_start: Called before starting the monitoring. * @after_wmarks_check: Called after each schemes' watermarks check. - * @after_sampling: Called after each sampling. * @after_aggregation: Called after each aggregation. - * @before_damos_apply: Called before applying DAMOS action. * @before_terminate: Called before terminating the monitoring. - * @private: User private data. * - * The monitoring thread (&damon_ctx.kdamond) calls @before_start and - * @before_terminate just before starting and finishing the monitoring, - * respectively. Therefore, those are good places for installing and cleaning - * @private. + * The monitoring thread (&damon_ctx.kdamond) calls @before_terminate just + * before finishing the monitoring. * * The monitoring thread calls @after_wmarks_check after each DAMON-based * operation schemes' watermarks check. If users need to make changes to the * attributes of the monitoring context while it's deactivated due to the * watermarks, this is the good place to do. * - * The monitoring thread calls @after_sampling and @after_aggregation for each - * of the sampling intervals and aggregation intervals, respectively. - * Therefore, users can safely access the monitoring results without additional - * protection. For the reason, users are recommended to use these callback for - * the accesses to the results. + * The monitoring thread calls @after_aggregation for each of the aggregation + * intervals. Therefore, users can safely access the monitoring results + * without additional protection. For the reason, users are recommended to use + * these callback for the accesses to the results. * * If any callback returns non-zero, monitoring stops. */ struct damon_callback { - void *private; - - int (*before_start)(struct damon_ctx *context); int (*after_wmarks_check)(struct damon_ctx *context); - int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); - int (*before_damos_apply)(struct damon_ctx *context, - struct damon_target *target, - struct damon_region *region, - struct damos *scheme); void (*before_terminate)(struct damon_ctx *context); }; @@ -633,11 +647,37 @@ struct damon_call_control { }; /** + * struct damon_intervals_goal - Monitoring intervals auto-tuning goal. + * + * @access_bp: Access events observation ratio to achieve in bp. + * @aggrs: Number of aggregations to acheive @access_bp within. + * @min_sample_us: Minimum resulting sampling interval in microseconds. + * @max_sample_us: Maximum resulting sampling interval in microseconds. + * + * DAMON automatically tunes &damon_attrs->sample_interval and + * &damon_attrs->aggr_interval aiming the ratio in bp (1/10,000) of + * DAMON-observed access events to theoretical maximum amount within @aggrs + * aggregations be same to @access_bp. The logic increases + * &damon_attrs->aggr_interval and &damon_attrs->sampling_interval in same + * ratio if the current access events observation ratio is lower than the + * target for each @aggrs aggregations, and vice versa. + * + * If @aggrs is zero, the tuning is disabled and hence this struct is ignored. + */ +struct damon_intervals_goal { + unsigned long access_bp; + unsigned long aggrs; + unsigned long min_sample_us; + unsigned long max_sample_us; +}; + +/** * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. * @ops_update_interval: The time between monitoring operations updates. + * @intervals_goal: Intervals auto-tuning goal. * @min_nr_regions: The minimum number of adaptive monitoring * regions. * @max_nr_regions: The maximum number of adaptive monitoring @@ -657,8 +697,20 @@ struct damon_attrs { unsigned long sample_interval; unsigned long aggr_interval; unsigned long ops_update_interval; + struct damon_intervals_goal intervals_goal; unsigned long min_nr_regions; unsigned long max_nr_regions; +/* private: internal use only */ + /* + * @aggr_interval to @sample_interval ratio. + * Core-external components call damon_set_attrs() with &damon_attrs + * that this field is unset. In the case, damon_set_attrs() sets this + * field of resulting &damon_attrs. Core-internal components such as + * kdamond_tune_intervals() calls damon_set_attrs() with &damon_attrs + * that this field is set. In the case, damon_set_attrs() just keep + * it. + */ + unsigned long aggr_samples; }; /** @@ -707,6 +759,11 @@ struct damon_ctx { * update */ unsigned long next_ops_update_sis; + /* + * number of sample intervals that should be passed before next + * intervals tuning + */ + unsigned long next_intervals_tune_sis; /* for waiting until the execution of the kdamond_fn is started */ struct completion kdamond_started; /* for scheme quotas prioritization */ @@ -788,6 +845,12 @@ static inline unsigned long damon_sz_region(struct damon_region *r) #define damos_for_each_filter_safe(f, next, scheme) \ list_for_each_entry_safe(f, next, &(scheme)->filters, list) +#define damos_for_each_ops_filter(f, scheme) \ + list_for_each_entry(f, &(scheme)->ops_filters, list) + +#define damos_for_each_ops_filter_safe(f, next, scheme) \ + list_for_each_entry_safe(f, next, &(scheme)->ops_filters, list) + #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); @@ -813,6 +876,7 @@ void damon_update_region_access_rate(struct damon_region *r, bool accessed, struct damos_filter *damos_new_filter(enum damos_filter_type type, bool matching, bool allow); void damos_add_filter(struct damos *s, struct damos_filter *f); +bool damos_filter_for_ops(enum damos_filter_type type); void damos_destroy_filter(struct damos_filter *f); struct damos_quota_goal *damos_new_quota_goal( diff --git a/include/linux/dax.h b/include/linux/dax.h index df41a0017b31..dcc9fcdf14e4 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -207,6 +207,11 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); +static inline bool dax_page_is_idle(struct page *page) +{ + return page && page_ref_count(page) == 0; +} + #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); @@ -220,6 +225,19 @@ static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ + +#if !IS_ENABLED(CONFIG_FS_DAX) +static inline int __must_check dax_break_layout(struct inode *inode, + loff_t start, loff_t end, void (cb)(struct inode *)) +{ + return 0; +} + +static inline void dax_break_layout_final(struct inode *inode) +{ +} +#endif + bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, @@ -241,8 +259,18 @@ vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); +void dax_delete_mapping_range(struct address_space *mapping, + loff_t start, loff_t end); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); +int __must_check dax_break_layout(struct inode *inode, loff_t start, + loff_t end, void (cb)(struct inode *)); +static inline int __must_check dax_break_layout_inode(struct inode *inode, + void (cb)(struct inode *)) +{ + return dax_break_layout(inode, 0, LLONG_MAX, cb); +} +void dax_break_layout_final(struct inode *inode); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same, diff --git a/include/linux/device.h b/include/linux/device.h index e3d56cd13fea..79e49fe494b7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1162,7 +1162,7 @@ static inline void device_remove_group(struct device *dev, { const struct attribute_group *groups[] = { grp, NULL }; - return device_remove_groups(dev, groups); + device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 45ee3a634999..65880e60c720 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -193,7 +193,7 @@ static inline int __must_check class_create_file(const struct class *class, static inline void class_remove_file(const struct class *class, const struct class_attribute *attr) { - return class_remove_file_ns(class, attr, NULL); + class_remove_file_ns(class, attr, NULL); } /* Simple class attribute that is just a static string */ diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h index 2dea217629d0..5d43881e6fb7 100644 --- a/include/linux/dma/k3-udma-glue.h +++ b/include/linux/dma/k3-udma-glue.h @@ -138,8 +138,7 @@ int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_num); void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_num, void *data, - void (*cleanup)(void *data, dma_addr_t desc_dma), - bool skip_fdq); + void (*cleanup)(void *data, dma_addr_t desc_dma)); int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_idx); int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn, diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 346251bf1026..bb146c5ac3e4 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -839,7 +839,6 @@ struct dma_filter { * The function takes a buffer of size buf_len. The callback function will * be called after period_len bytes have been transferred. * @device_prep_interleaved_dma: Transfer expression in a generic way. - * @device_prep_dma_imm_data: DMA's 8 byte immediate data to the dst address * @device_caps: May be used to override the generic DMA slave capabilities * with per-channel specific ones * @device_config: Pushes a new configuration to a channel, return 0 or an error @@ -942,9 +941,6 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)( struct dma_chan *chan, struct dma_interleaved_template *xt, unsigned long flags); - struct dma_async_tx_descriptor *(*device_prep_dma_imm_data)( - struct dma_chan *chan, dma_addr_t dst, u64 data, - unsigned long flags); void (*device_caps)(struct dma_chan *chan, struct dma_slave_caps *caps); int (*device_config)(struct dma_chan *chan, struct dma_slave_config *config); @@ -1639,14 +1635,14 @@ static inline struct dma_chan { struct dma_chan *chan; - chan = dma_request_slave_channel(dev, name); - if (chan) + chan = dma_request_chan(dev, name); + if (!IS_ERR(chan)) return chan; if (!fn || !fn_param) return NULL; - return __dma_request_channel(&mask, fn, fn_param, NULL); + return dma_request_channel(mask, fn, fn_param); } static inline char * diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index a087606ace19..fc93f0abf513 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -279,10 +279,22 @@ struct export_operations { atomic attribute updates */ #define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ -#define EXPORT_OP_ASYNC_LOCK (0x40) /* fs can do async lock request */ +#define EXPORT_OP_NOLOCKS (0x40) /* no file locking support */ unsigned long flags; }; +/** + * exportfs_cannot_lock() - check if export implements file locking + * @export_ops: the nfs export operations to check + * + * Returns true if the export does not support file locking. + */ +static inline bool +exportfs_cannot_lock(const struct export_operations *export_ops) +{ + return export_ops->flags & EXPORT_OP_NOLOCKS; +} + extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); diff --git a/include/linux/fb.h b/include/linux/fb.h index 5ba187e08cf7..cd653862ab99 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -225,6 +225,7 @@ struct fb_deferred_io { int open_count; /* number of opened files; protected by fb_info lock */ struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ + struct address_space *mapping; /* page cache object for fb device */ /* callback */ struct page *(*get_page)(struct fb_info *info, unsigned long offset); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h index 4d3f8074c137..45ad2408a80c 100644 --- a/include/linux/folio_queue.h +++ b/include/linux/folio_queue.h @@ -15,6 +15,7 @@ #define _LINUX_FOLIO_QUEUE_H #include <linux/pagevec.h> +#include <linux/mm.h> /* * Segment in a queue of running buffers. Each segment can hold a number of @@ -216,13 +217,6 @@ static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot) clear_bit(slot, &folioq->marks3); } -static inline unsigned int __folio_order(struct folio *folio) -{ - if (!folio_test_large(folio)) - return 0; - return folio->_flags_1 & 0xff; -} - /** * folioq_append: Add a folio to a folio queue segment * @folioq: The segment to add to @@ -241,7 +235,7 @@ static inline unsigned int folioq_append(struct folio_queue *folioq, struct foli unsigned int slot = folioq->vec.nr++; folioq->vec.folios[slot] = folio; - folioq->orders[slot] = __folio_order(folio); + folioq->orders[slot] = folio_order(folio); return slot; } @@ -263,7 +257,7 @@ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct unsigned int slot = folioq->vec.nr++; folioq->vec.folios[slot] = folio; - folioq->orders[slot] = __folio_order(folio); + folioq->orders[slot] = folio_order(folio); folioq_mark(folioq, slot); return slot; } diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 99f30c7d6208..897d6211c163 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -417,8 +417,6 @@ int __must_check fsl_mc_portal_allocate(struct fsl_mc_device *mc_dev, void fsl_mc_portal_free(struct fsl_mc_io *mc_io); -int fsl_mc_portal_reset(struct fsl_mc_io *mc_io); - int __must_check fsl_mc_object_allocate(struct fsl_mc_device *mc_dev, enum fsl_mc_pool_type pool_type, struct fsl_mc_device **new_mc_adev); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 88e078871158..1adcba3ddd76 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -231,8 +231,6 @@ static inline enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) /* Exported timer functions: */ /* Initialize timers: */ -extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, - enum hrtimer_mode mode); extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_setup_on_stack(struct hrtimer *timer, diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h index ad66a3081735..8fbbb6bdf7a1 100644 --- a/include/linux/hrtimer_types.h +++ b/include/linux/hrtimer_types.h @@ -34,12 +34,12 @@ enum hrtimer_restart { * @is_hard: Set if hrtimer will be expired in hard interrupt context * even on RT. * - * The hrtimer structure must be initialized by hrtimer_init() + * The hrtimer structure must be initialized by hrtimer_setup() */ struct hrtimer { struct timerqueue_node node; ktime_t _softexpires; - enum hrtimer_restart (*function)(struct hrtimer *); + enum hrtimer_restart (*__private function)(struct hrtimer *); struct hrtimer_clock_base *base; u8 state; u8 is_rel; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 93e509b6c00e..e893d546a49f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,6 +39,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, + bool write); +vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, + bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_UNSUPPORTED, @@ -341,6 +345,36 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); int min_order_for_split(struct folio *folio); int split_folio_to_list(struct folio *folio, struct list_head *list); +bool uniform_split_supported(struct folio *folio, unsigned int new_order, + bool warns); +bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, + bool warns); +int folio_split(struct folio *folio, unsigned int new_order, struct page *page, + struct list_head *list); +/* + * try_folio_split - try to split a @folio at @page using non uniform split. + * @folio: folio to be split + * @page: split to order-0 at the given page + * @list: store the after-split folios + * + * Try to split a @folio at @page using non uniform split to order-0, if + * non uniform split is not supported, fall back to uniform split. + * + * Return: 0: split is successful, otherwise split failed. + */ +static inline int try_folio_split(struct folio *folio, struct page *page, + struct list_head *list) +{ + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + if (!non_uniform_split_supported(folio, 0, false)) + return split_huge_page_to_list_to_order(&folio->page, list, + ret); + return folio_split(folio, ret, page, list); +} static inline int split_huge_page(struct page *page) { struct folio *folio = page_folio(page); @@ -404,7 +438,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, - unsigned long end, long adjust_next); + unsigned long end, struct vm_area_struct *next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); @@ -533,6 +567,12 @@ static inline int split_folio_to_list(struct folio *folio, struct list_head *lis return 0; } +static inline int try_folio_split(struct folio *folio, struct page *page, + struct list_head *list) +{ + return 0; +} + static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) @@ -571,7 +611,7 @@ static inline int madvise_collapse(struct vm_area_struct *vma, static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, - long adjust_next) + struct vm_area_struct *next) { } static inline int is_swap_pmd(pmd_t pmd) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 76a75ec03dd6..8f3ac832ee7f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -174,6 +174,9 @@ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; +void hugetlb_bootmem_alloc(void); +bool hugetlb_bootmem_allocated(void); + /* arch callbacks */ #ifndef CONFIG_HIGHPTE @@ -588,6 +591,7 @@ enum hugetlb_page_flags { HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, + HPG_cma, __NR_HPAGEFLAGS, }; @@ -647,6 +651,7 @@ HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) +HPAGEFLAG(Cma, cma) #ifdef CONFIG_HUGETLB_PAGE @@ -675,11 +680,21 @@ struct hstate { char name[HSTATE_NAME_LEN]; }; +struct cma; + struct huge_bootmem_page { struct list_head list; struct hstate *hstate; + unsigned long flags; + struct cma *cma; }; +#define HUGE_BOOTMEM_HVO 0x0001 +#define HUGE_BOOTMEM_ZONES_VALID 0x0002 +#define HUGE_BOOTMEM_CMA 0x0004 + +bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m); + int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); void wait_for_freed_hugetlb_folios(void); @@ -815,6 +830,17 @@ static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, } #endif +#ifndef arch_has_huge_bootmem_alloc +/* + * Some architectures do their own bootmem allocation, so they can't use + * early CMA allocation. + */ +static inline bool arch_has_huge_bootmem_alloc(void) +{ + return false; +} +#endif + static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); @@ -1257,6 +1283,15 @@ static inline bool hugetlbfs_pagecache_present( { return false; } + +static inline void hugetlb_bootmem_alloc(void) +{ +} + +static inline bool hugetlb_bootmem_allocated(void) +{ + return false; +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 2b2af24d2a43..2e4903b7f7bc 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -952,6 +952,21 @@ static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg) return (msg->addr << 1) | (msg->flags & I2C_M_RD); } +/* + * 10-bit address + * addr_1: 5'b11110 | addr[9:8] | (R/nW) + * addr_2: addr[7:0] + */ +static inline u8 i2c_10bit_addr_hi_from_msg(const struct i2c_msg *msg) +{ + return 0xf0 | ((msg->addr & GENMASK(9, 8)) >> 7) | (msg->flags & I2C_M_RD); +} + +static inline u8 i2c_10bit_addr_lo_from_msg(const struct i2c_msg *msg) +{ + return msg->addr & GENMASK(7, 0); +} + u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold); void i2c_put_dma_safe_msg_buf(u8 *buf, struct i2c_msg *msg, bool xferred); @@ -1029,10 +1044,6 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node return i2c_get_adapter_by_fwnode(of_fwnode_handle(node)); } -const struct of_device_id -*i2c_of_match_device(const struct of_device_id *matches, - struct i2c_client *client); - int of_i2c_get_board_info(struct device *dev, struct device_node *node, struct i2c_board_info *info); @@ -1053,13 +1064,6 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node return NULL; } -static inline const struct of_device_id -*i2c_of_match_device(const struct of_device_id *matches, - struct i2c_client *client) -{ - return NULL; -} - static inline int of_i2c_get_board_info(struct device *dev, struct device_node *node, struct i2c_board_info *info) diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 12d532b012c5..c67922ece617 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -475,7 +475,7 @@ struct i3c_master_controller_ops { int (*attach_i2c_dev)(struct i2c_dev_desc *dev); void (*detach_i2c_dev)(struct i2c_dev_desc *dev); int (*i2c_xfers)(struct i2c_dev_desc *dev, - const struct i2c_msg *xfers, int nxfers); + struct i2c_msg *xfers, int nxfers); int (*request_ibi)(struct i3c_dev_desc *dev, const struct i3c_ibi_setup *req); void (*free_ibi)(struct i3c_dev_desc *dev); diff --git a/include/linux/idr.h b/include/linux/idr.h index cd729be369b3..2267902d29a7 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -274,6 +274,7 @@ struct ida { int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); void ida_free(struct ida *, unsigned int id); void ida_destroy(struct ida *ida); +int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max); /** * ida_alloc() - Allocate an unused ID. @@ -345,4 +346,14 @@ static inline bool ida_is_empty(const struct ida *ida) { return xa_empty(&ida->xa); } + +static inline bool ida_exists(struct ida *ida, unsigned int id) +{ + return ida_find_first_range(ida, id, id) == id; +} + +static inline int ida_find_first(struct ida *ida) +{ + return ida_find_first_range(ida, 0, ~0); +} #endif /* __IDR_H__ */ diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 417073c52380..f242b285081b 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -46,6 +46,7 @@ struct iio_dev; * modify or drop the sample data, it, may be NULL. * @has_registers: true if the device has writable and readable registers, false * if there is just one read-only sample data shift register. + * @has_named_irqs: Set to true if there is more than one IRQ line. * @addr_shift: Shift of the register address in the communications register. * @read_mask: Mask for the communications register having the read bit set. * @status_ch_mask: Mask for the channel number stored in status register. @@ -53,7 +54,6 @@ struct iio_dev; * be used. * @irq_flags: flags for the interrupt used by the triggered buffer * @num_slots: Number of sequencer slots - * @irq_line: IRQ for reading conversions. If 0, spi->irq will be used * @num_resetclks: Number of SPI clk cycles with MOSI=1 to reset the chip. */ struct ad_sigma_delta_info { @@ -64,13 +64,13 @@ struct ad_sigma_delta_info { int (*disable_one)(struct ad_sigma_delta *, unsigned int chan); int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample); bool has_registers; + bool has_named_irqs; unsigned int addr_shift; unsigned int read_mask; unsigned int status_ch_mask; unsigned int data_reg; unsigned long irq_flags; unsigned int num_slots; - int irq_line; unsigned int num_resetclks; }; diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index 10be00f3b120..e45b7dfbec35 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -70,6 +70,12 @@ enum iio_backend_sample_trigger { IIO_BACKEND_SAMPLE_TRIGGER_MAX }; +enum iio_backend_interface_type { + IIO_BACKEND_INTERFACE_SERIAL_LVDS, + IIO_BACKEND_INTERFACE_SERIAL_CMOS, + IIO_BACKEND_INTERFACE_MAX +}; + /** * struct iio_backend_ops - operations structure for an iio_backend * @enable: Enable backend. @@ -88,6 +94,9 @@ enum iio_backend_sample_trigger { * @extend_chan_spec: Extend an IIO channel. * @ext_info_set: Extended info setter. * @ext_info_get: Extended info getter. + * @interface_type_get: Interface type. + * @data_size_set: Data size. + * @oversampling_ratio_set: Set Oversampling ratio. * @read_raw: Read a channel attribute from a backend device * @debugfs_print_chan_status: Print channel status into a buffer. * @debugfs_reg_access: Read or write register value of backend. @@ -128,6 +137,11 @@ struct iio_backend_ops { const char *buf, size_t len); int (*ext_info_get)(struct iio_backend *back, uintptr_t private, const struct iio_chan_spec *chan, char *buf); + int (*interface_type_get)(struct iio_backend *back, + enum iio_backend_interface_type *type); + int (*data_size_set)(struct iio_backend *back, unsigned int size); + int (*oversampling_ratio_set)(struct iio_backend *back, + unsigned int ratio); int (*read_raw)(struct iio_backend *back, struct iio_chan_spec const *chan, int *val, int *val2, long mask); @@ -186,6 +200,11 @@ ssize_t iio_backend_ext_info_set(struct iio_dev *indio_dev, uintptr_t private, const char *buf, size_t len); ssize_t iio_backend_ext_info_get(struct iio_dev *indio_dev, uintptr_t private, const struct iio_chan_spec *chan, char *buf); +int iio_backend_interface_type_get(struct iio_backend *back, + enum iio_backend_interface_type *type); +int iio_backend_data_size_set(struct iio_backend *back, unsigned int size); +int iio_backend_oversampling_ratio_set(struct iio_backend *back, + unsigned int ratio); int iio_backend_read_raw(struct iio_backend *back, struct iio_chan_spec const *chan, int *val, int *val2, long mask); diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index 81d9a19aeb91..37f27545f69f 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -11,8 +11,9 @@ struct iio_dev; struct device; +struct dma_chan; -void iio_dmaengine_buffer_free(struct iio_buffer *buffer); +void iio_dmaengine_buffer_teardown(struct iio_buffer *buffer); struct iio_buffer *iio_dmaengine_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, const char *channel, @@ -26,6 +27,10 @@ int devm_iio_dmaengine_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, const char *channel, enum iio_buffer_direction dir); +int devm_iio_dmaengine_buffer_setup_with_handle(struct device *dev, + struct iio_dev *indio_dev, + struct dma_chan *chan, + enum iio_buffer_direction dir); #define devm_iio_dmaengine_buffer_setup(dev, indio_dev, channel) \ devm_iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel, \ diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index e5de7a124bad..66f830ab9b49 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -208,5 +208,6 @@ int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, int *length); int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time, const int **vals, int *type, int *length); +int iio_gts_get_total_gain(struct iio_gts *gts, int gain, int time); #endif diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 56161e02f002..07a0e8132e88 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -9,7 +9,7 @@ #include <linux/device.h> #include <linux/cdev.h> -#include <linux/cleanup.h> +#include <linux/compiler_types.h> #include <linux/slab.h> #include <linux/iio/types.h> /* IIO TODO LIST */ @@ -663,30 +663,29 @@ int iio_device_claim_direct_mode(struct iio_dev *indio_dev); void iio_device_release_direct_mode(struct iio_dev *indio_dev); /* - * This autocleanup logic is normally used via - * iio_device_claim_direct_scoped(). + * Helper functions that allow claim and release of direct mode + * in a fashion that doesn't generate many false positives from sparse. + * Note this must remain static inline in the header so that sparse + * can see the __acquire() marking. Revisit when sparse supports + * __cond_acquires() */ -DEFINE_GUARD(iio_claim_direct, struct iio_dev *, iio_device_claim_direct_mode(_T), - iio_device_release_direct_mode(_T)) +static inline bool iio_device_claim_direct(struct iio_dev *indio_dev) +{ + int ret = iio_device_claim_direct_mode(indio_dev); -DEFINE_GUARD_COND(iio_claim_direct, _try, ({ - struct iio_dev *dev; - int d = iio_device_claim_direct_mode(_T); + if (ret) + return false; - if (d < 0) - dev = NULL; - else - dev = _T; - dev; - })) + __acquire(iio_dev); -/** - * iio_device_claim_direct_scoped() - Scoped call to iio_device_claim_direct. - * @fail: What to do on failure to claim device. - * @iio_dev: Pointer to the IIO devices structure - */ -#define iio_device_claim_direct_scoped(fail, iio_dev) \ - scoped_cond_guard(iio_claim_direct_try, fail, iio_dev) + return true; +} + +static inline void iio_device_release_direct(struct iio_dev *indio_dev) +{ + iio_device_release_direct_mode(indio_dev); + __release(indio_dev); +} int iio_device_claim_buffer_mode(struct iio_dev *indio_dev); void iio_device_release_buffer_mode(struct iio_dev *indio_dev); diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 4bb98d9731de..aa160511e265 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -44,6 +44,8 @@ struct adis_timeout { * @glob_cmd_reg: Register address of the GLOB_CMD register * @msc_ctrl_reg: Register address of the MSC_CTRL register * @diag_stat_reg: Register address of the DIAG_STAT register + * @diag_stat_size: Length (in bytes) of the DIAG_STAT register. If 0 the + * default length is 2 bytes long. * @prod_id_reg: Register address of the PROD_ID register * @prod_id: Product ID code that should be expected when reading @prod_id_reg * @self_test_mask: Bitmask of supported self-test operations @@ -70,6 +72,7 @@ struct adis_data { unsigned int glob_cmd_reg; unsigned int msc_ctrl_reg; unsigned int diag_stat_reg; + unsigned int diag_stat_size; unsigned int prod_id_reg; unsigned int prod_id; @@ -95,12 +98,28 @@ struct adis_data { }; /** + * struct adis_ops: Custom ops for adis devices. + * @write: Custom spi write implementation. + * @read: Custom spi read implementation. + * @reset: Custom sw reset implementation. The custom implementation does not + * need to sleep after the reset. It's done by the library already. + */ +struct adis_ops { + int (*write)(struct adis *adis, unsigned int reg, unsigned int value, + unsigned int size); + int (*read)(struct adis *adis, unsigned int reg, unsigned int *value, + unsigned int size); + int (*reset)(struct adis *adis); +}; + +/** * struct adis - ADIS device instance data * @spi: Reference to SPI device which owns this ADIS IIO device * @trig: IIO trigger object data * @data: ADIS chip variant specific data * @burst_extra_len: Burst extra length. Should only be used by devices that can * dynamically change their burst mode length. + * @ops: ops struct for custom read and write functions * @state_lock: Lock used by the device to protect state * @msg: SPI message object * @xfer: SPI transfer objects to be used for a @msg @@ -116,6 +135,7 @@ struct adis { const struct adis_data *data; unsigned int burst_extra_len; + const struct adis_ops *ops; /** * The state_lock is meant to be used during operations that require * a sequence of SPI R/W in order to protect the SPI transfer @@ -168,7 +188,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, u8 val) { - return __adis_write_reg(adis, reg, val, 1); + return adis->ops->write(adis, reg, val, 1); } /** @@ -180,7 +200,7 @@ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, u16 val) { - return __adis_write_reg(adis, reg, val, 2); + return adis->ops->write(adis, reg, val, 2); } /** @@ -192,7 +212,7 @@ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, u32 val) { - return __adis_write_reg(adis, reg, val, 4); + return adis->ops->write(adis, reg, val, 4); } /** @@ -207,7 +227,7 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, unsigned int tmp; int ret; - ret = __adis_read_reg(adis, reg, &tmp, 2); + ret = adis->ops->read(adis, reg, &tmp, 2); if (ret == 0) *val = tmp; @@ -226,7 +246,7 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, unsigned int tmp; int ret; - ret = __adis_read_reg(adis, reg, &tmp, 4); + ret = adis->ops->read(adis, reg, &tmp, 4); if (ret == 0) *val = tmp; @@ -244,7 +264,7 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size) { guard(mutex)(&adis->state_lock); - return __adis_write_reg(adis, reg, val, size); + return adis->ops->write(adis, reg, val, size); } /** @@ -258,7 +278,7 @@ static int adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, unsigned int size) { guard(mutex)(&adis->state_lock); - return __adis_read_reg(adis, reg, val, size); + return adis->ops->read(adis, reg, val, size); } /** diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index aaa8a0767aa3..1b400f26f63d 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -104,12 +104,8 @@ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \ if (ITSTART(node) <= last) { /* Cond1 */ \ if (start <= ITLAST(node)) /* Cond2 */ \ return node; /* node is leftmost match */ \ - if (node->ITRB.rb_right) { \ - node = rb_entry(node->ITRB.rb_right, \ - ITSTRUCT, ITRB); \ - if (start <= node->ITSUBTREE) \ - continue; \ - } \ + node = rb_entry(node->ITRB.rb_right, ITSTRUCT, ITRB); \ + continue; \ } \ return NULL; /* No match */ \ } \ diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index e6723fa95160..0634a3de1782 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -21,7 +21,6 @@ struct io_uring_cmd { struct io_uring_cmd_data { void *op_data; - struct io_uring_sqe sqes[2]; }; static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 02fe001feebb..68416b135151 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -79,6 +79,11 @@ struct vm_fault; #define IOMAP_F_ATOMIC_BIO (1U << 8) /* + * Flag reserved for file system specific usage + */ +#define IOMAP_F_PRIVATE (1U << 12) + +/* * Flags set by the core iomap code during operations: * * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size @@ -88,14 +93,8 @@ struct vm_fault; * range it covers needs to be remapped by the high level before the operation * can proceed. */ -#define IOMAP_F_SIZE_CHANGED (1U << 8) -#define IOMAP_F_STALE (1U << 9) - -/* - * Flags from 0x1000 up are for file system specific usage: - */ -#define IOMAP_F_PRIVATE (1U << 12) - +#define IOMAP_F_SIZE_CHANGED (1U << 14) +#define IOMAP_F_STALE (1U << 15) /* * Magic value for addr: diff --git a/include/linux/iommu.h b/include/linux/iommu.h index cf8c16ba04a0..ccce8a751e2a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -41,6 +41,7 @@ struct iommu_dirty_ops; struct notifier_block; struct iommu_sva; struct iommu_dma_cookie; +struct iommu_dma_msi_cookie; struct iommu_fault_param; struct iommufd_ctx; struct iommufd_viommu; @@ -165,6 +166,15 @@ struct iommu_domain_geometry { bool force_aperture; /* DMA only allowed in mappable range? */ }; +enum iommu_domain_cookie_type { + IOMMU_COOKIE_NONE, + IOMMU_COOKIE_DMA_IOVA, + IOMMU_COOKIE_DMA_MSI, + IOMMU_COOKIE_FAULT_HANDLER, + IOMMU_COOKIE_SVA, + IOMMU_COOKIE_IOMMUFD, +}; + /* Domain feature flags */ #define __IOMMU_DOMAIN_PAGING (1U << 0) /* Support for iommu_map/unmap */ #define __IOMMU_DOMAIN_DMA_API (1U << 1) /* Domain for use in DMA-API @@ -211,23 +221,18 @@ struct iommu_domain_geometry { struct iommu_domain { unsigned type; + enum iommu_domain_cookie_type cookie_type; const struct iommu_domain_ops *ops; const struct iommu_dirty_ops *dirty_ops; const struct iommu_ops *owner; /* Whose domain_alloc we came from */ unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ struct iommu_domain_geometry geometry; - struct iommu_dma_cookie *iova_cookie; int (*iopf_handler)(struct iopf_group *group); -#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) - int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, - phys_addr_t msi_addr); -#endif - - union { /* Pointer usable by owner of the domain */ - struct iommufd_hw_pagetable *iommufd_hwpt; /* iommufd */ - }; - union { /* Fault handler */ + union { /* cookie */ + struct iommu_dma_cookie *iova_cookie; + struct iommu_dma_msi_cookie *msi_cookie; + struct iommufd_hw_pagetable *iommufd_hwpt; struct { iommu_fault_handler_t handler; void *handler_token; @@ -244,16 +249,6 @@ struct iommu_domain { }; }; -static inline void iommu_domain_set_sw_msi( - struct iommu_domain *domain, - int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, - phys_addr_t msi_addr)) -{ -#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) - domain->sw_msi = sw_msi; -#endif -} - static inline bool iommu_is_dma_domain(struct iommu_domain *domain) { return domain->type & __IOMMU_DOMAIN_DMA_API; diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 11110c749200..34b6e6ca4bfa 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -8,9 +8,11 @@ #include <linux/err.h> #include <linux/errno.h> +#include <linux/iommu.h> #include <linux/refcount.h> #include <linux/types.h> #include <linux/xarray.h> +#include <uapi/linux/iommufd.h> struct device; struct file; @@ -34,6 +36,7 @@ enum iommufd_object_type { IOMMUFD_OBJ_FAULT, IOMMUFD_OBJ_VIOMMU, IOMMUFD_OBJ_VDEVICE, + IOMMUFD_OBJ_VEVENTQ, #ifdef CONFIG_IOMMUFD_TEST IOMMUFD_OBJ_SELFTEST, #endif @@ -52,9 +55,11 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx, struct device *dev, u32 *id); void iommufd_device_unbind(struct iommufd_device *idev); -int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id); -int iommufd_device_replace(struct iommufd_device *idev, u32 *pt_id); -void iommufd_device_detach(struct iommufd_device *idev); +int iommufd_device_attach(struct iommufd_device *idev, ioasid_t pasid, + u32 *pt_id); +int iommufd_device_replace(struct iommufd_device *idev, ioasid_t pasid, + u32 *pt_id); +void iommufd_device_detach(struct iommufd_device *idev, ioasid_t pasid); struct iommufd_ctx *iommufd_device_to_ictx(struct iommufd_device *idev); u32 iommufd_device_to_id(struct iommufd_device *idev); @@ -93,6 +98,8 @@ struct iommufd_viommu { const struct iommufd_viommu_ops *ops; struct xarray vdevs; + struct list_head veventqs; + struct rw_semaphore veventqs_rwsem; unsigned int type; }; @@ -187,6 +194,11 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, enum iommufd_object_type type); struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id); +int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu, + struct device *dev, unsigned long *vdev_id); +int iommufd_viommu_report_event(struct iommufd_viommu *viommu, + enum iommu_veventq_type type, void *event_data, + size_t data_len); #else /* !CONFIG_IOMMUFD_DRIVER_CORE */ static inline struct iommufd_object * _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, @@ -200,6 +212,20 @@ iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) { return NULL; } + +static inline int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu, + struct device *dev, + unsigned long *vdev_id) +{ + return -ENOENT; +} + +static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, + enum iommu_veventq_type type, + void *event_data, size_t data_len) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_IOMMUFD_DRIVER_CORE */ /* diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 5385349f0b8a..e8b2d6aa4013 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -154,15 +154,20 @@ enum { }; /* helpers to define resources */ -#define DEFINE_RES_NAMED(_start, _size, _name, _flags) \ +#define DEFINE_RES_NAMED_DESC(_start, _size, _name, _flags, _desc) \ (struct resource) { \ .start = (_start), \ .end = (_start) + (_size) - 1, \ .name = (_name), \ .flags = (_flags), \ - .desc = IORES_DESC_NONE, \ + .desc = (_desc), \ } +#define DEFINE_RES_NAMED(_start, _size, _name, _flags) \ + DEFINE_RES_NAMED_DESC(_start, _size, _name, _flags, IORES_DESC_NONE) +#define DEFINE_RES(_start, _size, _flags) \ + DEFINE_RES_NAMED(_start, _size, NULL, _flags) + #define DEFINE_RES_IO_NAMED(_start, _size, _name) \ DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_IO) #define DEFINE_RES_IO(_start, _size) \ diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 33ff41eef8f7..bb7111105296 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -72,7 +72,7 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, /** * struct irq_domain_ops - Methods for irq_domain objects - * @match: Match an interrupt controller device node to a host, returns + * @match: Match an interrupt controller device node to a domain, returns * 1 on a match * @select: Match an interrupt controller fw specification. It is more generic * than @match as it receives a complete struct irq_fwspec. Therefore, @@ -352,8 +352,8 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, void *host_data); struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); -void irq_set_default_host(struct irq_domain *host); -struct irq_domain *irq_get_default_host(void); +void irq_set_default_domain(struct irq_domain *domain); +struct irq_domain *irq_get_default_domain(void); int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, irq_hw_number_t hwirq, int node, const struct irq_affinity_desc *affinity); @@ -454,7 +454,7 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod return IS_ERR(d) ? NULL : d; } -unsigned int irq_create_direct_mapping(struct irq_domain *host); +unsigned int irq_create_direct_mapping(struct irq_domain *domain); #endif static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, @@ -507,7 +507,7 @@ static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fw return IS_ERR(d) ? NULL : d; } -void irq_domain_remove(struct irq_domain *host); +void irq_domain_remove(struct irq_domain *domain); int irq_domain_associate(struct irq_domain *domain, unsigned int irq, irq_hw_number_t hwirq); @@ -515,16 +515,16 @@ void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, irq_hw_number_t hwirq_base, int count); -unsigned int irq_create_mapping_affinity(struct irq_domain *host, +unsigned int irq_create_mapping_affinity(struct irq_domain *domain, irq_hw_number_t hwirq, const struct irq_affinity_desc *affinity); unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); void irq_dispose_mapping(unsigned int virq); -static inline unsigned int irq_create_mapping(struct irq_domain *host, +static inline unsigned int irq_create_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { - return irq_create_mapping_affinity(host, hwirq, NULL); + return irq_create_mapping_affinity(domain, hwirq, NULL); } struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 905a2e2f45f6..ecbf819deeca 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -104,7 +104,7 @@ extern int kdb_initial_cpu; #define KDB_NOENVVALUE (-6) #define KDB_NOTIMP (-7) #define KDB_ENVFULL (-8) -#define KDB_ENVBUFFULL (-9) +#define KDB_KMALLOCFAILED (-9) #define KDB_TOOMANYBPT (-10) #define KDB_TOOMANYDBREGS (-11) #define KDB_DUPBPT (-12) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 87c79d076d6d..b5a5f32fdfd1 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -147,6 +147,11 @@ enum kernfs_root_flag { * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, + + /* + * Renames must not change the parent node. + */ + KERNFS_ROOT_INVARIANT_PARENT = 0x0010, }; /* type-specific structures for kernfs_node union members */ @@ -199,8 +204,8 @@ struct kernfs_node { * never moved to a different parent, it is safe to access the * parent directly. */ - struct kernfs_node *parent; - const char *name; + struct kernfs_node __rcu *__parent; + const char __rcu *name; struct rb_node rb; @@ -395,7 +400,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); -int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, +int kernfs_path_from_node(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); @@ -416,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); +unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, @@ -514,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } +static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ return 0; } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, diff --git a/include/linux/kexec.h b/include/linux/kexec.h index c840431eadda..c8971861521a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -203,6 +203,15 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif +#ifndef arch_check_excluded_range +static inline int arch_check_excluded_range(struct kimage *image, + unsigned long start, + unsigned long end) +{ + return 0; +} +#endif + #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len); diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 51ef131e66b7..5eebbe7a3545 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -257,7 +257,6 @@ extern void kgdb_arch_late(void); * hardware breakpoints. * @correct_hw_break: Allow an architecture to specify how to correct the * hardware debug registers. - * @enable_nmi: Manage NMI-triggered entry to KGDB */ struct kgdb_arch { unsigned char gdb_bpt_instr[BREAK_INSTR_SIZE]; @@ -270,8 +269,6 @@ struct kgdb_arch { void (*disable_hw_break)(struct pt_regs *regs); void (*remove_all_hw_break)(void); void (*correct_hw_break)(void); - - void (*enable_nmi)(bool on); }; /** @@ -306,14 +303,6 @@ extern const struct kgdb_arch arch_kgdb_ops; extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); -#ifdef CONFIG_SERIAL_KGDB_NMI -extern int kgdb_register_nmi_console(void); -extern int kgdb_unregister_nmi_console(void); -#else -static inline int kgdb_register_nmi_console(void) { return 0; } -static inline int kgdb_unregister_nmi_console(void) { return 0; } -#endif - extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops); extern struct kgdb_io *dbg_io_ops; diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 5c8865bb59d9..b11660b706c5 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -134,10 +134,6 @@ .size name, .-name #endif -/* If symbol 'name' is treated as a subroutine (gets called, and returns) - * then please use ENDPROC to mark 'name' as STT_FUNC for the benefit of - * static analysis tools such as stack depth analyzer. - */ #ifndef ENDPROC /* deprecated, use SYM_FUNC_END */ #define ENDPROC(name) \ diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index fa6e8471bd22..248db9b77ee2 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -28,6 +28,7 @@ struct hlist_nulls_node { #define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) +#define HLIST_NULLS_HEAD_INIT(nulls) {.first = (struct hlist_nulls_node *)NULLS_MARKER(nulls)} #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index b38a56a13f39..725fd7727422 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -97,8 +97,6 @@ ssize_t mei_cldev_send(struct mei_cl_device *cldev, const u8 *buf, ssize_t mei_cldev_send_timeout(struct mei_cl_device *cldev, const u8 *buf, size_t length, unsigned long timeout); ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); -ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf, - size_t length); ssize_t mei_cldev_recv_timeout(struct mei_cl_device *cldev, u8 *buf, size_t length, unsigned long timeout); ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, const u8 *buf, @@ -107,8 +105,6 @@ ssize_t mei_cldev_send_vtag_timeout(struct mei_cl_device *cldev, const u8 *buf, size_t length, u8 vtag, unsigned long timeout); ssize_t mei_cldev_recv_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length, u8 *vtag); -ssize_t mei_cldev_recv_nonblock_vtag(struct mei_cl_device *cldev, u8 *buf, - size_t length, u8 *vtag); ssize_t mei_cldev_recv_vtag_timeout(struct mei_cl_device *cldev, u8 *buf, size_t length, u8 *vtag, unsigned long timeout); @@ -116,7 +112,6 @@ int mei_cldev_register_rx_cb(struct mei_cl_device *cldev, mei_cldev_cb_t rx_cb); int mei_cldev_register_notif_cb(struct mei_cl_device *cldev, mei_cldev_cb_t notif_cb); -const uuid_le *mei_cldev_uuid(const struct mei_cl_device *cldev); u8 mei_cldev_ver(const struct mei_cl_device *cldev); void *mei_cldev_get_drvdata(const struct mei_cl_device *cldev); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e79eb6ac516f..ef5a1ecc6e59 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -133,7 +133,6 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size); -void memblock_free_all(void); void memblock_free(void *ptr, size_t size); void reset_all_zones_managed_pages(void); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6e74b8254d9b..53364526d877 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -438,9 +438,7 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) */ static inline bool folio_memcg_charged(struct folio *folio) { - if (folio_memcg_kmem(folio)) - return __folio_objcg(folio) != NULL; - return __folio_memcg(folio) != NULL; + return folio->memcg_data != 0; } /* @@ -649,8 +647,6 @@ int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); -void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); - void __mem_cgroup_uncharge(struct folio *folio); /** @@ -1040,7 +1036,9 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -void split_page_memcg(struct page *head, int old_order, int new_order); +void split_page_memcg(struct page *first, unsigned order); +void folio_split_memcg_refs(struct folio *folio, unsigned old_order, + unsigned new_order); static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { @@ -1165,10 +1163,6 @@ static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, return 0; } -static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr) -{ -} - static inline void mem_cgroup_uncharge(struct folio *folio) { } @@ -1465,7 +1459,12 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } -static inline void split_page_memcg(struct page *head, int old_order, int new_order) +static inline void split_page_memcg(struct page *first, unsigned order) +{ +} + +static inline void folio_split_memcg_refs(struct folio *folio, + unsigned old_order, unsigned new_order) { } @@ -1848,6 +1847,9 @@ static inline void mem_cgroup_exit_user_fault(void) current->in_user_fault = 0; } +void memcg1_swapout(struct folio *folio, swp_entry_t entry); +void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages); + #else /* CONFIG_MEMCG_V1 */ static inline unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, @@ -1875,6 +1877,14 @@ static inline void mem_cgroup_exit_user_fault(void) { } +static inline void memcg1_swapout(struct folio *folio, swp_entry_t entry) +{ +} + +static inline void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages) +{ +} + #endif /* CONFIG_MEMCG_V1 */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memory.h b/include/linux/memory.h index c0afee5d126e..12daa6ec7d09 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -25,7 +25,7 @@ /** * struct memory_group - a logical group of memory blocks * @nid: The node id for all memory blocks inside the memory group. - * @blocks: List of all memory blocks belonging to this memory group. + * @memory_blocks: List of all memory blocks belonging to this memory group. * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this * memory group. * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 3f7143ade32c..4aa151914eab 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -161,7 +161,7 @@ static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; + page_pgmap(page)->type == MEMORY_DEVICE_PRIVATE; } static inline bool folio_is_device_private(const struct folio *folio) @@ -173,13 +173,13 @@ static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; + page_pgmap(page)->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_device_coherent_page(const struct page *page) { return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_COHERENT; + page_pgmap(page)->type == MEMORY_DEVICE_COHERENT; } static inline bool folio_is_device_coherent(const struct folio *folio) @@ -187,6 +187,17 @@ static inline bool folio_is_device_coherent(const struct folio *folio) return is_device_coherent_page(&folio->page); } +static inline bool is_fsdax_page(const struct page *page) +{ + return is_zone_device_page(page) && + page_pgmap(page)->type == MEMORY_DEVICE_FS_DAX; +} + +static inline bool folio_is_fsdax(const struct folio *folio) +{ + return is_fsdax_page(&folio->page); +} + #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index 068ae1c0f0e8..27883af44f87 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -60,11 +60,6 @@ #define RTC_PDN2 0x002e #define RTC_PDN2_PWRON_ALARM BIT(4) -#define RTC_MIN_YEAR 1968 -#define RTC_BASE_YEAR 1900 -#define RTC_NUM_YEARS 128 -#define RTC_MIN_YEAR_OFFSET (RTC_MIN_YEAR - RTC_BASE_YEAR) - #define MTK_RTC_POLL_DELAY_US 10 #define MTK_RTC_POLL_TIMEOUT (jiffies_to_usecs(HZ)) diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 059dc94d20bb..dd372b0123a6 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -721,12 +721,6 @@ enum mhi_state mhi_get_mhi_state(struct mhi_controller *mhi_cntrl); void mhi_soc_reset(struct mhi_controller *mhi_cntrl); /** - * mhi_device_get - Disable device low power mode - * @mhi_dev: Device associated with the channel - */ -void mhi_device_get(struct mhi_device *mhi_dev); - -/** * mhi_device_get_sync - Disable device low power mode. Synchronously * take the controller out of suspended state * @mhi_dev: Device associated with the channel @@ -777,18 +771,6 @@ int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev); /** - * mhi_queue_dma - Send or receive DMA mapped buffers from client device - * over MHI channel - * @mhi_dev: Device associated with the channels - * @dir: DMA direction for the channel - * @mhi_buf: Buffer for holding the DMA mapped data - * @len: Buffer length - * @mflags: MHI transfer flags used for the transfer - */ -int mhi_queue_dma(struct mhi_device *mhi_dev, enum dma_data_direction dir, - struct mhi_buf *mhi_buf, size_t len, enum mhi_flags mflags); - -/** * mhi_queue_buf - Send or receive raw buffers from client device over MHI * channel * @mhi_dev: Device associated with the channels diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 80891120cca9..aaa2114498d6 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -205,8 +205,8 @@ struct migrate_vma { unsigned long end; /* - * Set to the owner value also stored in page->pgmap->owner for - * migrating out of device private memory. The flags also need to + * Set to the owner value also stored in page_pgmap(page)->owner + * for migrating out of device private memory. The flags also need to * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE. * The caller should always set this field when using mmu notifier * callbacks to avoid device MMU invalidations for device private diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index 1160bed6579e..79ddc0adbf2b 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -218,7 +218,7 @@ static size_t parent(size_t i, unsigned int lsbit, size_t size) /* Initialize a min-heap. */ static __always_inline -void __min_heap_init_inline(min_heap_char *heap, void *data, int size) +void __min_heap_init_inline(min_heap_char *heap, void *data, size_t size) { heap->nr = 0; heap->size = size; @@ -254,7 +254,7 @@ bool __min_heap_full_inline(min_heap_char *heap) /* Sift the element at pos down the heap. */ static __always_inline -void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size, +void __min_heap_sift_down_inline(min_heap_char *heap, size_t pos, size_t elem_size, const struct min_heap_callbacks *func, void *args) { const unsigned long lsbit = elem_size & -elem_size; @@ -324,7 +324,7 @@ static __always_inline void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args) { - int i; + ssize_t i; for (i = heap->nr / 2 - 1; i >= 0; i--) __min_heap_sift_down_inline(heap, i, elem_size, func, args); @@ -379,7 +379,7 @@ bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t ele const struct min_heap_callbacks *func, void *args) { void *data = heap->data; - int pos; + size_t pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) return false; @@ -428,10 +428,10 @@ bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx, __min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) -void __min_heap_init(min_heap_char *heap, void *data, int size); +void __min_heap_init(min_heap_char *heap, void *data, size_t size); void *__min_heap_peek(struct min_heap_char *heap); bool __min_heap_full(min_heap_char *heap); -void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size, +void __min_heap_sift_down(min_heap_char *heap, size_t pos, size_t elem_size, const struct min_heap_callbacks *func, void *args); void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args); diff --git a/include/linux/mm.h b/include/linux/mm.h index 4a50ba8002e9..b7f13f087954 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -32,6 +32,7 @@ #include <linux/memremap.h> #include <linux/slab.h> #include <linux/cacheinfo.h> +#include <linux/rcuwait.h> struct mempolicy; struct anon_vma; @@ -40,20 +41,10 @@ struct user_struct; struct pt_regs; struct folio_batch; +void arch_mm_preinit(void); void mm_core_init(void); void init_mm_internals(void); -#ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ -extern unsigned long max_mapnr; - -static inline void set_max_mapnr(unsigned long limit) -{ - max_mapnr = limit; -} -#else -static inline void set_max_mapnr(unsigned long limit) { } -#endif - extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { @@ -242,8 +233,6 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); -/* Use only if VMA has no other users */ -void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -682,13 +671,57 @@ static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_PER_VMA_LOCK +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + static struct lock_class_key lockdep_key; + + lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0); +#endif + if (reset_refcnt) + refcount_set(&vma->vm_refcnt, 0); + vma->vm_lock_seq = UINT_MAX; +} + +static inline bool is_vma_writer_only(int refcnt) +{ + /* + * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma + * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on + * a detached vma happens only in vma_mark_detached() and is a rare + * case, therefore most of the time there will be no unnecessary wakeup. + */ + return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1; +} + +static inline void vma_refcount_put(struct vm_area_struct *vma) +{ + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *mm = vma->vm_mm; + int oldcnt; + + rwsem_release(&vma->vmlock_dep_map, _RET_IP_); + if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { + + if (is_vma_writer_only(oldcnt - 1)) + rcuwait_wake_up(&mm->vma_writer_wait); + } +} + /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. + * False locked result is possible if mm_lock_seq overflows or if vma gets + * reused and attached to a different mm before we lock it. + * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got + * detached. */ -static inline bool vma_start_read(struct vm_area_struct *vma) +static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, + struct vm_area_struct *vma) { + int oldcnt; + /* * Check before locking. A race might cause false locked result. * We can use READ_ONCE() for the mm_lock_seq here, and don't need @@ -696,16 +729,26 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence)) - return false; + if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) + return NULL; - if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) - return false; + /* + * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire() + * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET. + * Acquire fence is required here to avoid reordering against later + * vm_lock_seq check and checks inside lock_vma_under_rcu(). + */ + if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, + VMA_REF_LIMIT))) { + /* return EAGAIN if vma got detached from under us */ + return oldcnt ? NULL : ERR_PTR(-EAGAIN); + } + rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); /* - * Overflow might produce false locked result. + * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq + * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq * modification invalidates all existing locks. * * We must use ACQUIRE semantics for the mm_lock_seq so that if we are @@ -713,18 +756,47 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ - if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) { - up_read(&vma->vm_lock->lock); - return false; + if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) { + vma_refcount_put(vma); + return NULL; } + + return vma; +} + +/* + * Use only while holding mmap read lock which guarantees that locking will not + * fail (nobody can concurrently write-lock the vma). vma_start_read() should + * not be used in such cases because it might fail due to mm_lock_seq overflow. + * This functionality is used to obtain vma read lock and drop the mmap read lock. + */ +static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) +{ + int oldcnt; + + mmap_assert_locked(vma->vm_mm); + if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, + VMA_REF_LIMIT))) + return false; + + rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); return true; } +/* + * Use only while holding mmap read lock which guarantees that locking will not + * fail (nobody can concurrently write-lock the vma). vma_start_read() should + * not be used in such cases because it might fail due to mm_lock_seq overflow. + * This functionality is used to obtain vma read lock and drop the mmap read lock. + */ +static inline bool vma_start_read_locked(struct vm_area_struct *vma) +{ + return vma_start_read_locked_nested(vma, 0); +} + static inline void vma_end_read(struct vm_area_struct *vma) { - rcu_read_lock(); /* keeps vma alive till the end of up_read */ - up_read(&vma->vm_lock->lock); - rcu_read_unlock(); + vma_refcount_put(vma); } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ @@ -740,6 +812,8 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_l return (vma->vm_lock_seq == *mm_lock_seq); } +void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq); + /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently @@ -752,15 +826,7 @@ static inline void vma_start_write(struct vm_area_struct *vma) if (__is_vma_write_locked(vma, &mm_lock_seq)) return; - down_write(&vma->vm_lock->lock); - /* - * We should use WRITE_ONCE() here because we can have concurrent reads - * from the early lockless pessimistic check in vma_start_read(). - * We don't really care about the correctness of that early check, but - * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. - */ - WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); - up_write(&vma->vm_lock->lock); + __vma_start_write(vma, mm_lock_seq); } static inline void vma_assert_write_locked(struct vm_area_struct *vma) @@ -772,18 +838,36 @@ static inline void vma_assert_write_locked(struct vm_area_struct *vma) static inline void vma_assert_locked(struct vm_area_struct *vma) { - if (!rwsem_is_locked(&vma->vm_lock->lock)) - vma_assert_write_locked(vma); + unsigned int mm_lock_seq; + + VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 && + !__is_vma_write_locked(vma, &mm_lock_seq), vma); } -static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +/* + * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these + * assertions should be made either under mmap_write_lock or when the object + * has been isolated under mmap_write_lock, ensuring no competing writers. + */ +static inline void vma_assert_attached(struct vm_area_struct *vma) { - /* When detaching vma should be write-locked */ - if (detached) - vma_assert_write_locked(vma); - vma->detached = detached; + WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); +} + +static inline void vma_assert_detached(struct vm_area_struct *vma) +{ + WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); +} + +static inline void vma_mark_attached(struct vm_area_struct *vma) +{ + vma_assert_write_locked(vma); + vma_assert_detached(vma); + refcount_set_release(&vma->vm_refcnt, 1); } +void vma_mark_detached(struct vm_area_struct *vma); + static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) @@ -805,14 +889,18 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, #else /* CONFIG_PER_VMA_LOCK */ -static inline bool vma_start_read(struct vm_area_struct *vma) - { return false; } +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} +static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, + struct vm_area_struct *vma) + { return NULL; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } -static inline void vma_mark_detached(struct vm_area_struct *vma, - bool detached) {} +static inline void vma_assert_attached(struct vm_area_struct *vma) {} +static inline void vma_assert_detached(struct vm_area_struct *vma) {} +static inline void vma_mark_attached(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) @@ -839,18 +927,13 @@ static inline void assert_fault_locked(struct vm_fault *vmf) extern const struct vm_operations_struct vma_dummy_vm_ops; -/* - * WARNING: vma_init does not initialize vma->vm_lock. - * Use vm_area_alloc()/vm_area_free() if vma needs locking. - */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); - vma_mark_detached(vma, false); - vma_numab_state_init(vma); + vma_lock_init(vma, false); } /* Use when VMA is not part of the VMA tree and needs no locking */ @@ -1043,6 +1126,7 @@ static inline int vma_iter_bulk_store(struct vma_iterator *vmi, if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; + vma_mark_attached(vma); return 0; } @@ -1083,6 +1167,25 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +extern void prep_compound_page(struct page *page, unsigned int order); + +static inline unsigned int folio_large_order(const struct folio *folio) +{ + return folio->_flags_1 & 0xff; +} + +#ifdef NR_PAGES_IN_LARGE_FOLIO +static inline long folio_large_nr_pages(const struct folio *folio) +{ + return folio->_nr_pages; +} +#else +static inline long folio_large_nr_pages(const struct folio *folio) +{ + return 1L << folio_large_order(folio); +} +#endif + /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be @@ -1096,7 +1199,7 @@ static inline unsigned int compound_order(struct page *page) if (!test_bit(PG_head, &folio->flags)) return 0; - return folio->_flags_1 & 0xff; + return folio_large_order(folio); } /** @@ -1112,7 +1215,7 @@ static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; - return folio->_flags_1 & 0xff; + return folio_large_order(folio); } #include <linux/huge_mm.h> @@ -1205,6 +1308,8 @@ static inline int is_vmalloc_or_module_addr(const void *x) static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1)) + return 0; return atomic_read(&folio->_entire_mapcount) + 1; } @@ -1404,25 +1509,6 @@ vm_fault_t finish_fault(struct vm_fault *vmf); * back into memory. */ -#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) -DECLARE_STATIC_KEY_FALSE(devmap_managed_key); - -bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); -static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) -{ - if (!static_branch_unlikely(&devmap_managed_key)) - return false; - if (!folio_is_zone_device(folio)) - return false; - return __put_devmap_managed_folio_refs(folio, refs); -} -#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) -{ - return false; -} -#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) @@ -1543,12 +1629,6 @@ static inline void put_page(struct page *page) if (folio_test_slab(folio)) return; - /* - * For some devmap managed pages we need to catch refcount transition - * from 2 to 1: - */ - if (put_devmap_managed_folio_refs(folio, 1)) - return; folio_put(folio); } @@ -1907,6 +1987,13 @@ static inline struct folio *pfn_folio(unsigned long pfn) return page_folio(pfn_to_page(pfn)); } +static inline bool folio_has_pincount(const struct folio *folio) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return folio_test_large(folio); + return folio_order(folio) > 1; +} + /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. @@ -1923,7 +2010,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * - * For large folios, the result will be exactly correct. That's because + * For most large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * @@ -1934,7 +2021,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { - if (folio_test_large(folio)) + if (folio_has_pincount(folio)) return atomic_read(&folio->_pincount) > 0; /* @@ -2006,6 +2093,13 @@ static inline bool folio_is_longterm_pinnable(struct folio *folio) if (folio_is_device_coherent(folio)) return false; + /* + * Filesystems can only tolerate transient delays to truncate and + * hole-punch operations + */ + if (folio_is_fsdax(folio)) + return false; + /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); @@ -2049,11 +2143,7 @@ static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; -#ifdef CONFIG_64BIT - return folio->_folio_nr_pages; -#else - return 1L << (folio->_flags_1 & 0xff); -#endif + return folio_large_nr_pages(folio); } /* Only hugetlbfs can allocate folios larger than MAX_ORDER */ @@ -2068,24 +2158,20 @@ static inline long folio_nr_pages(const struct folio *folio) * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ -static inline unsigned long compound_nr(struct page *page) +static inline long compound_nr(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 1; -#ifdef CONFIG_64BIT - return folio->_folio_nr_pages; -#else - return 1L << (folio->_flags_1 & 0xff); -#endif + return folio_large_nr_pages(folio); } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ -static inline int thp_nr_pages(struct page *page) +static inline long thp_nr_pages(struct page *page) { return folio_nr_pages((struct folio *)page); } @@ -2140,23 +2226,18 @@ static inline size_t folio_size(const struct folio *folio) } /** - * folio_likely_mapped_shared - Estimate if the folio is mapped into the page - * tables of more than one MM + * folio_maybe_mapped_shared - Whether the folio is mapped into the page + * tables of more than one MM * @folio: The folio. * - * This function checks if the folio is currently mapped into more than one - * MM ("mapped shared"), or if the folio is only mapped into a single MM - * ("mapped exclusively"). + * This function checks if the folio maybe currently mapped into more than one + * MM ("maybe mapped shared"), or if the folio is certainly mapped into a single + * MM ("mapped exclusively"). * * For KSM folios, this function also returns "mapped shared" when a folio is * mapped multiple times into the same MM, because the individual page mappings * are independent. * - * As precise information is not easily available for all folios, this function - * estimates the number of MMs ("sharers") that are currently mapping a folio - * using the number of times the first page of the folio is currently mapped - * into page tables. - * * For small anonymous folios and anonymous hugetlb folios, the return * value will be exactly correct: non-KSM folios can only be mapped at most once * into an MM, and they cannot be partially mapped. KSM folios are @@ -2164,8 +2245,8 @@ static inline size_t folio_size(const struct folio *folio) * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly - * indicate "mapped exclusively" (false negative) when the folio is - * only partially mapped into at least one MM. + * indicate "mapped shared" (false positive) if a folio was mapped by + * more than two MMs at one point in time. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. @@ -2182,7 +2263,7 @@ static inline size_t folio_size(const struct folio *folio) * * Return: Whether the folio is estimated to be mapped into more than one MM. */ -static inline bool folio_likely_mapped_shared(struct folio *folio) +static inline bool folio_maybe_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); @@ -2190,16 +2271,22 @@ static inline bool folio_likely_mapped_shared(struct folio *folio) if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; - /* A single mapping implies "mapped exclusively". */ - if (mapcount <= 1) - return false; - - /* If any page is mapped more than once we treat it "mapped shared". */ - if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) + /* + * vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ... + * simply assume "mapped shared", nobody should really care + * about this for arbitrary kernel allocations. + */ + if (!IS_ENABLED(CONFIG_MM_ID)) return true; - /* Let's guess based on the first subpage. */ - return atomic_read(&folio->_mapcount) > 0; + /* + * A single mapping implies "mapped exclusively", even if the + * folio flag says something different: it's easier to handle this + * case here instead of on the RMAP hot path. + */ + if (mapcount <= 1) + return false; + return folio_test_large_maybe_mapped_shared(folio); } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE @@ -2408,11 +2495,13 @@ struct follow_pfnmap_args { * Outputs: * * @pfn: the PFN of the address + * @addr_mask: address mask covering pfn * @pgprot: the pgprot_t of the mapping * @writable: whether the mapping is writable * @special: whether the mapping is a special mapping (real PFN maps) */ unsigned long pfn; + unsigned long addr_mask; pgprot_t pgprot; bool writable; bool special; @@ -3179,7 +3268,6 @@ extern void reserve_bootmem_region(phys_addr_t start, /* Free the reserved page into the buddy system, so it gets managed. */ void free_reserved_page(struct page *page); -#define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { @@ -3539,6 +3627,8 @@ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); +vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page, + bool write); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, @@ -3817,6 +3907,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) #endif void *sparse_buffer_alloc(unsigned long size); +unsigned long section_map_size(void); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); @@ -3825,7 +3916,8 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap, struct page *reuse); + struct vmem_altmap *altmap, unsigned long ptpfn, + unsigned long flags); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, @@ -3841,6 +3933,12 @@ int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); +int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); +int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); +void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, @@ -3907,9 +4005,6 @@ static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, } #endif -void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, - unsigned long nr_pages); - enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, @@ -4110,6 +4205,7 @@ void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); +int reserve_mem_release_by_name(const char *name); #ifdef CONFIG_64BIT int do_mseal(unsigned long start, size_t len_in, unsigned long flags); @@ -4142,4 +4238,14 @@ int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *st int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); + +/* + * mseal of userspace process's system mappings. + */ +#ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS +#define VM_SEALED_SYSMAP VM_SEALED +#else +#define VM_SEALED_SYSMAP VM_NONE +#endif + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 75e8850cec3a..56d07edd01f9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -19,6 +19,7 @@ #include <linux/workqueue.h> #include <linux/seqlock.h> #include <linux/percpu_counter.h> +#include <linux/types.h> #include <asm/mmu.h> @@ -133,8 +134,11 @@ struct page { unsigned long compound_head; /* Bit zero is set */ }; struct { /* ZONE_DEVICE pages */ - /** @pgmap: Points to the hosting device page map. */ - struct dev_pagemap *pgmap; + /* + * The first word is used for compound_head or folio + * pgmap + */ + void *_unused_pgmap_compound_head; void *zone_device_data; /* * ZONE_DEVICE private pages are counted as being @@ -287,6 +291,49 @@ typedef struct { unsigned long val; } swp_entry_t; +#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT) +/* We have some extra room after the refcount in tail pages. */ +#define NR_PAGES_IN_LARGE_FOLIO +#endif + +/* + * On 32bit, we can cut the required metadata in half, because: + * (a) PID_MAX_LIMIT implicitly limits the number of MMs we could ever have, + * so we can limit MM IDs to 15 bit (32767). + * (b) We don't expect folios where even a single complete PTE mapping by + * one MM would exceed 15 bits (order-15). + */ +#ifdef CONFIG_64BIT +typedef int mm_id_mapcount_t; +#define MM_ID_MAPCOUNT_MAX INT_MAX +typedef unsigned int mm_id_t; +#else /* !CONFIG_64BIT */ +typedef short mm_id_mapcount_t; +#define MM_ID_MAPCOUNT_MAX SHRT_MAX +typedef unsigned short mm_id_t; +#endif /* CONFIG_64BIT */ + +/* We implicitly use the dummy ID for init-mm etc. where we never rmap pages. */ +#define MM_ID_DUMMY 0 +#define MM_ID_MIN (MM_ID_DUMMY + 1) + +/* + * We leave the highest bit of each MM id unused, so we can store a flag + * in the highest bit of each folio->_mm_id[]. + */ +#define MM_ID_BITS ((sizeof(mm_id_t) * BITS_PER_BYTE) - 1) +#define MM_ID_MASK ((1U << MM_ID_BITS) - 1) +#define MM_ID_MAX MM_ID_MASK + +/* + * In order to use bit_spin_lock(), which requires an unsigned long, we + * operate on folio->_mm_ids when working on flags. + */ +#define FOLIO_MM_IDS_LOCK_BITNUM MM_ID_BITS +#define FOLIO_MM_IDS_LOCK_BIT BIT(FOLIO_MM_IDS_LOCK_BITNUM) +#define FOLIO_MM_IDS_SHARED_BITNUM (2 * MM_ID_BITS + 1) +#define FOLIO_MM_IDS_SHARED_BIT BIT(FOLIO_MM_IDS_SHARED_BITNUM) + /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. @@ -296,6 +343,8 @@ typedef struct { * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, * this is the index from the beginning of the mmap. + * @share: number of DAX mappings that reference this folio. See + * dax_associate_entry. * @private: Filesystem per-folio data (see folio_attach_private()). * @swap: Used for swp_entry_t if folio_test_swapcache(). * @_mapcount: Do not access this member directly. Use folio_mapcount() to @@ -303,13 +352,17 @@ typedef struct { * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. + * @pgmap: Metadata for ZONE_DEVICE mappings * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_large_mapcount: Do not use directly, call folio_mapcount(). * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). - * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). + * @_nr_pages: Do not use directly, call folio_nr_pages(). + * @_mm_id: Do not use outside of rmap code. + * @_mm_ids: Do not use outside of rmap code. + * @_mm_id_mapcount: Do not use outside of rmap code. * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. @@ -341,9 +394,13 @@ struct folio { /* private: */ }; /* public: */ + struct dev_pagemap *pgmap; }; struct address_space *mapping; - pgoff_t index; + union { + pgoff_t index; + unsigned long share; + }; union { void *private; swp_entry_t swap; @@ -369,14 +426,30 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; + union { + struct { /* public: */ - atomic_t _large_mapcount; - atomic_t _entire_mapcount; - atomic_t _nr_pages_mapped; - atomic_t _pincount; + atomic_t _large_mapcount; + atomic_t _nr_pages_mapped; #ifdef CONFIG_64BIT - unsigned int _folio_nr_pages; -#endif + atomic_t _entire_mapcount; + atomic_t _pincount; +#endif /* CONFIG_64BIT */ + mm_id_mapcount_t _mm_id_mapcount[2]; + union { + mm_id_t _mm_id[2]; + unsigned long _mm_ids; + }; + /* private: the union with struct page is transitional */ + }; + unsigned long _usable_1[4]; + }; + atomic_t _mapcount_1; + atomic_t _refcount_1; + /* public: */ +#ifdef NR_PAGES_IN_LARGE_FOLIO + unsigned int _nr_pages; +#endif /* NR_PAGES_IN_LARGE_FOLIO */ /* private: the union with struct page is transitional */ }; struct page __page_1; @@ -386,20 +459,27 @@ struct folio { unsigned long _flags_2; unsigned long _head_2; /* public: */ - void *_hugetlb_subpool; - void *_hugetlb_cgroup; - void *_hugetlb_cgroup_rsvd; - void *_hugetlb_hwpoison; + struct list_head _deferred_list; +#ifndef CONFIG_64BIT + atomic_t _entire_mapcount; + atomic_t _pincount; +#endif /* !CONFIG_64BIT */ /* private: the union with struct page is transitional */ }; + struct page __page_2; + }; + union { struct { - unsigned long _flags_2a; - unsigned long _head_2a; + unsigned long _flags_3; + unsigned long _head_3; /* public: */ - struct list_head _deferred_list; + void *_hugetlb_subpool; + void *_hugetlb_cgroup; + void *_hugetlb_cgroup_rsvd; + void *_hugetlb_hwpoison; /* private: the union with struct page is transitional */ }; - struct page __page_2; + struct page __page_3; }; }; @@ -428,14 +508,20 @@ FOLIO_MATCH(_last_cpupid, _last_cpupid); offsetof(struct page, pg) + sizeof(struct page)) FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); +FOLIO_MATCH(_mapcount, _mapcount_1); +FOLIO_MATCH(_refcount, _refcount_1); #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ offsetof(struct page, pg) + 2 * sizeof(struct page)) FOLIO_MATCH(flags, _flags_2); FOLIO_MATCH(compound_head, _head_2); -FOLIO_MATCH(flags, _flags_2a); -FOLIO_MATCH(compound_head, _head_2a); +#undef FOLIO_MATCH +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct folio, fl) == \ + offsetof(struct page, pg) + 3 * sizeof(struct page)) +FOLIO_MATCH(flags, _flags_3); +FOLIO_MATCH(compound_head, _head_3); #undef FOLIO_MATCH /** @@ -578,6 +664,12 @@ static inline void *folio_get_private(struct folio *folio) typedef unsigned long vm_flags_t; /* + * freeptr_t represents a SLUB freelist pointer, which might be encoded + * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. + */ +typedef struct { unsigned long v; } freeptr_t; + +/* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. @@ -633,9 +725,8 @@ static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) } #endif -struct vma_lock { - struct rw_semaphore lock; -}; +#define VMA_LOCK_OFFSET 0x40000000 +#define VMA_REF_LIMIT (VMA_LOCK_OFFSET - 1) struct vma_numab_state { /* @@ -681,6 +772,9 @@ struct vma_numab_state { * * Only explicitly marked struct members may be accessed by RCU readers before * getting a stable reference. + * + * WARNING: when adding new members, please update vm_area_init_from() to copy + * them during vm_area_struct content duplication. */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ @@ -691,9 +785,7 @@ struct vm_area_struct { unsigned long vm_start; unsigned long vm_end; }; -#ifdef CONFIG_PER_VMA_LOCK - struct rcu_head vm_rcu; /* Used for deferred freeing. */ -#endif + freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */ }; /* @@ -714,18 +806,12 @@ struct vm_area_struct { #ifdef CONFIG_PER_VMA_LOCK /* - * Flag to indicate areas detached from the mm->mm_mt tree. - * Unstable RCU readers are allowed to read this. - */ - bool detached; - - /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) - * - vm_lock->lock (in write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set * Can be read reliably while holding one of: * - mmap_lock (in read or write mode) - * - vm_lock->lock (in read or write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout * while holding nothing (except RCU to keep the VMA struct allocated). * @@ -734,20 +820,7 @@ struct vm_area_struct { * slowpath. */ unsigned int vm_lock_seq; - /* Unstable RCU readers are allowed to read this. */ - struct vma_lock *vm_lock; #endif - - /* - * For areas with an address space and backing store, - * linkage into the address_space->i_mmap interval tree. - * - */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; - /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma @@ -767,14 +840,6 @@ struct vm_area_struct { struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ -#ifdef CONFIG_ANON_VMA_NAME - /* - * For private and shared anonymous mappings, a pointer to a null - * terminated string containing the name given to the vma, or NULL if - * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. - */ - struct anon_vma_name *anon_name; -#endif #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; #endif @@ -787,6 +852,30 @@ struct vm_area_struct { #ifdef CONFIG_NUMA_BALANCING struct vma_numab_state *numab_state; /* NUMA Balancing state */ #endif +#ifdef CONFIG_PER_VMA_LOCK + /* Unstable RCU readers are allowed to read this. */ + refcount_t vm_refcnt ____cacheline_aligned_in_smp; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map vmlock_dep_map; +#endif +#endif + /* + * For areas with an address space and backing store, + * linkage into the address_space->i_mmap interval tree. + * + */ + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; +#ifdef CONFIG_ANON_VMA_NAME + /* + * For private and shared anonymous mappings, a pointer to a null + * terminated string containing the name given to the vma, or NULL if + * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. + */ + struct anon_vma_name *anon_name; +#endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; @@ -922,6 +1011,7 @@ struct mm_struct { * by mmlist_lock */ #ifdef CONFIG_PER_VMA_LOCK + struct rcuwait vma_writer_wait; /* * This field has lock-like semantics, meaning it is sometimes * accessed with ACQUIRE/RELEASE semantics. @@ -1074,6 +1164,9 @@ struct mm_struct { #endif } lru_gen; #endif /* CONFIG_LRU_GEN_WALKS_MMU */ +#ifdef CONFIG_MM_ID + mm_id_t mm_id; +#endif /* CONFIG_MM_ID */ } __randomize_layout; /* diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 45a21faa3ff6..4706c6769902 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -122,12 +122,6 @@ static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int #endif /* CONFIG_PER_VMA_LOCK */ -static inline void mmap_init_lock(struct mm_struct *mm) -{ - init_rwsem(&mm->mmap_lock); - mm_lock_seqcount_init(mm); -} - static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index e2dd57ca368b..bc2402a45741 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -43,10 +43,10 @@ struct mmu_interval_notifier; * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. * - * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no - * longer have exclusive access to the page. When sent during creation of an - * exclusive range the owner will be initialised to the value provided by the - * caller of make_device_exclusive_range(), otherwise the owner will be NULL. + * @MMU_NOTIFY_EXCLUSIVE: conversion of a page table entry to device-exclusive. + * The owner is initialized to the value provided by the caller of + * make_device_exclusive(), such that this caller can filter out these + * events. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e16939553930..25e80b2ca7f4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -138,6 +138,7 @@ enum numa_stat_item { enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, + NR_FREE_PAGES_BLOCKS, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, @@ -220,9 +221,11 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, + PGDEMOTE_PROACTIVE, #ifdef CONFIG_HUGETLB_PAGE NR_HUGETLB, #endif + NR_BALLOON_PAGES, NR_VM_NODE_STAT_ITEMS }; @@ -1161,6 +1164,12 @@ static inline bool is_zone_device_page(const struct page *page) return page_zonenum(page) == ZONE_DEVICE; } +static inline struct dev_pagemap *page_pgmap(const struct page *page) +{ + VM_WARN_ON_ONCE_PAGE(!is_zone_device_page(page), page); + return page_folio(page)->pgmap; +} + /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different @@ -1176,7 +1185,7 @@ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, return false; if (!is_zone_device_page(a)) return true; - return a->pgmap == b->pgmap; + return page_pgmap(a) == page_pgmap(b); } extern void memmap_init_zone_device(struct zone *, unsigned long, @@ -1191,6 +1200,10 @@ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, { return true; } +static inline struct dev_pagemap *page_pgmap(const struct page *page) +{ + return NULL; +} #endif static inline bool folio_is_zone_device(const struct folio *folio) @@ -1937,6 +1950,9 @@ enum { #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT + SECTION_IS_VMEMMAP_PREINIT_BIT, +#endif SECTION_MAP_LAST_BIT, }; @@ -1947,6 +1963,9 @@ enum { #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT +#define SECTION_IS_VMEMMAP_PREINIT BIT(SECTION_IS_VMEMMAP_PREINIT_BIT) +#endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT @@ -2001,6 +2020,30 @@ static inline int online_device_section(struct mem_section *section) } #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT +static inline int preinited_vmemmap_section(struct mem_section *section) +{ + return (section && + (section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT)); +} + +void sparse_vmemmap_init_nid_early(int nid); +void sparse_vmemmap_init_nid_late(int nid); + +#else +static inline int preinited_vmemmap_section(struct mem_section *section) +{ + return 0; +} +static inline void sparse_vmemmap_init_nid_early(int nid) +{ +} + +static inline void sparse_vmemmap_init_nid_late(int nid) +{ +} +#endif + static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); @@ -2038,6 +2081,9 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) } #endif +void sparse_init_early_section(int nid, struct page *map, unsigned long pnum, + unsigned long flags); + #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN @@ -2100,6 +2146,11 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr) return -1; } +#define for_each_present_section_nr(start, section_nr) \ + for (section_nr = next_present_section_nr(start - 1); \ + section_nr != -1; \ + section_nr = next_present_section_nr(section_nr)) + /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate @@ -2119,6 +2170,8 @@ void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) +#define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0) +#define sparse_vmemmap_init_nid_late(_nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ diff --git a/include/linux/module.h b/include/linux/module.h index d9a5183a9fe7..d94b196d5a34 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -771,6 +771,8 @@ static inline bool is_livepatch_module(struct module *mod) void set_module_sig_enforced(void); +void module_for_each_mod(int(*func)(struct module *mod, void *data), void *data); + #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) @@ -878,6 +880,10 @@ static inline bool module_is_coming(struct module *mod) { return false; } + +static inline void module_for_each_mod(int(*func)(struct module *mod, void *data), void *data) +{ +} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 2bf91b57591b..2143d05116be 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -202,4 +202,6 @@ DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T)) DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T)) DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0) +extern unsigned long mutex_get_owner(struct mutex *lock); + #endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fa79145518d1..cf3b6445817b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4192,7 +4192,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, int netif_set_alias(struct net_device *dev, const char *alias, size_t len); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); -int netif_change_net_namespace(struct net_device *dev, struct net *net, +int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack); int dev_change_net_namespace(struct net_device *dev, struct net *net, diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 9ac83ca88326..d8cad844870a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -300,6 +300,7 @@ enum nfsstat4 { /* error codes for internal client use */ #define NFS4ERR_RESET_TO_MDS 12001 #define NFS4ERR_RESET_TO_PNFS 12002 +#define NFS4ERR_FATAL_IOERROR 12003 static inline bool seqid_mutating_err(u32 err) { @@ -691,6 +692,7 @@ enum { NFSPROC4_CLNT_LISTXATTRS, NFSPROC4_CLNT_REMOVEXATTR, NFSPROC4_CLNT_READ_PLUS, + NFSPROC4_CLNT_OFFLOAD_STATUS, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index f00bfcee7120..71319637a84e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -50,6 +50,7 @@ struct nfs_client { #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ #define NFS_CS_PNFS 9 /* - Server used for pnfs */ +#define NFS_CS_NETUNREACH_FATAL 10 /* - ENETUNREACH errors are fatal */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -167,6 +168,8 @@ struct nfs_server { #define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 #define NFS_MOUNT_SHUTDOWN 0x08000000 #define NFS_MOUNT_NO_ALIGNWRITE 0x10000000 +#define NFS_MOUNT_FORCE_RDIRPLUS 0x20000000 +#define NFS_MOUNT_NETUNREACH_FATAL 0x40000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ @@ -250,6 +253,10 @@ struct nfs_server { struct list_head ss_copies; struct list_head ss_src_copies; + unsigned long delegation_flags; +#define NFS4SERV_DELEGRETURN (1) +#define NFS4SERV_DELEGATION_EXPIRED (2) +#define NFS4SERV_DELEGRETURN_DELAYED (3) unsigned long delegation_gen; unsigned long mig_gen; unsigned long mig_status; @@ -289,6 +296,7 @@ struct nfs_server { #define NFS_CAP_CASE_INSENSITIVE (1U << 6) #define NFS_CAP_CASE_PRESERVING (1U << 7) #define NFS_CAP_REBOOT_LAYOUTRETURN (1U << 8) +#define NFS_CAP_OFFLOAD_STATUS (1U << 9) #define NFS_CAP_OPEN_XOR (1U << 12) #define NFS_CAP_DELEGTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d66c61cbbd1d..67f6632f723b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1515,8 +1515,9 @@ struct nfs42_offload_status_args { struct nfs42_offload_status_res { struct nfs4_sequence_res osr_seq_res; - uint64_t osr_count; - int osr_status; + u64 osr_count; + int complete_count; + u32 osr_complete; }; struct nfs42_copy_notify_args { diff --git a/include/linux/node.h b/include/linux/node.h index 9a881c2208b3..2b7517892230 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -57,6 +57,11 @@ enum cache_write_policy { NODE_CACHE_WRITE_OTHER, }; +enum cache_mode { + NODE_CACHE_ADDR_MODE_RESERVED, + NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR, +}; + /** * struct node_cache_attrs - system memory caching attributes * @@ -65,6 +70,7 @@ enum cache_write_policy { * @size: Total size of cache in bytes * @line_size: Number of bytes fetched on a cache miss * @level: The cache hierarchy level + * @address_mode: The address mode */ struct node_cache_attrs { enum cache_indexing indexing; @@ -72,6 +78,7 @@ struct node_cache_attrs { u64 size; u16 line_size; u8 level; + u16 address_mode; }; #ifdef CONFIG_HMEM_REPORTING diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 3ca965a2ddc8..366ad004d794 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -69,7 +69,7 @@ * In asm, there are two kinds of code: normal C-type callable functions and * the rest. The normal callable functions can be called by other code, and * don't do anything unusual with the stack. Such normal callable functions - * are annotated with the ENTRY/ENDPROC macros. Most asm code falls in this + * are annotated with SYM_FUNC_{START,END}. Most asm code falls in this * category. In this case, no special debugging annotations are needed because * objtool can automatically generate the ORC data for the ORC unwinder to read * at runtime. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index df9234e5f478..e6a21b62dcce 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -226,11 +226,48 @@ static __always_inline const struct page *page_fixed_fake_head(const struct page } return page; } + +static __always_inline bool page_count_writable(const struct page *page, int u) +{ + if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) + return true; + + /* + * The refcount check is ordered before the fake-head check to prevent + * the following race: + * CPU 1 (HVO) CPU 2 (speculative PFN walker) + * + * page_ref_freeze() + * synchronize_rcu() + * rcu_read_lock() + * page_is_fake_head() is false + * vmemmap_remap_pte() + * XXX: struct page[] becomes r/o + * + * page_ref_unfreeze() + * page_ref_count() is not zero + * + * atomic_add_unless(&page->_refcount) + * XXX: try to modify r/o struct page[] + * + * The refcount check also prevents modification attempts to other (r/o) + * tail pages that are not fake heads. + */ + if (atomic_read_acquire(&page->_refcount) == u) + return false; + + return page_fixed_fake_head(page) == page; +} #else static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } + +static inline bool page_count_writable(const struct page *page, int u) +{ + return true; +} #endif static __always_inline int page_is_fake_head(const struct page *page) @@ -673,12 +710,6 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) -/* - * Different with flags above, this flag is used only for fsdax mode. It - * indicates that this page->mapping is now under reflink case. - */ -#define PAGE_MAPPING_DAX_SHARED ((void *)0x1) - static __always_inline bool folio_mapping_flags(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; @@ -1106,6 +1137,12 @@ static inline bool is_page_hwpoison(const struct page *page) return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } +static inline bool folio_contain_hwpoisoned_page(struct folio *folio) +{ + return folio_test_hwpoison(folio) || + (folio_test_large(folio) && folio_test_has_hwpoisoned(folio)); +} + bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); @@ -1193,6 +1230,10 @@ static inline int folio_has_private(const struct folio *folio) return !!(folio->flags & PAGE_FLAGS_PRIVATE); } +static inline bool folio_test_large_maybe_mapped_shared(const struct folio *folio) +{ + return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); +} #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 46406f3fe34d..d649b6bbbc87 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -9,10 +9,12 @@ struct page_counter { /* - * Make sure 'usage' does not share cacheline with any other field. The - * memcg->memory.usage is a hot member of struct mem_cgroup. + * Make sure 'usage' does not share cacheline with any other field in + * v2. The memcg->memory.usage is a hot member of struct mem_cgroup. */ atomic_long_t usage; + unsigned long failcnt; /* v1-only field */ + CACHELINE_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ @@ -28,12 +30,12 @@ struct page_counter { unsigned long watermark; /* Latest cg2 reset watermark */ unsigned long local_watermark; - unsigned long failcnt; /* Keep all the read most fields in a separete cacheline. */ CACHELINE_PADDING(_pad2_); bool protection_support; + bool track_failcnt; unsigned long min; unsigned long low; unsigned long high; @@ -58,6 +60,7 @@ static inline void page_counter_init(struct page_counter *counter, counter->max = PAGE_COUNTER_MAX; counter->parent = parent; counter->protection_support = protection_support; + counter->track_failcnt = false; } static inline unsigned long page_counter_read(struct page_counter *counter) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index e4b48a0dda24..76c817162d2f 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -3,6 +3,7 @@ #define __LINUX_PAGE_EXT_H #include <linux/types.h> +#include <linux/mmzone.h> #include <linux/stacktrace.h> struct pglist_data; @@ -69,16 +70,31 @@ extern void page_ext_init(void); static inline void page_ext_init_flatmem_late(void) { } + +static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn) +{ + /* + * page_ext is allocated per memory section. Once we cross a + * memory section, we have to fetch the new pointer. + */ + return next_pfn % PAGES_PER_SECTION; +} #else extern void page_ext_init_flatmem(void); extern void page_ext_init_flatmem_late(void); static inline void page_ext_init(void) { } + +static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn) +{ + return true; +} #endif extern struct page_ext *page_ext_get(const struct page *page); extern void page_ext_put(struct page_ext *page_ext); +extern struct page_ext *page_ext_lookup(unsigned long pfn); static inline void *page_ext_data(struct page_ext *page_ext, struct page_ext_operations *ops) @@ -93,6 +109,83 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr) return next; } +struct page_ext_iter { + unsigned long index; + unsigned long start_pfn; + struct page_ext *page_ext; +}; + +/** + * page_ext_iter_begin() - Prepare for iterating through page extensions. + * @iter: page extension iterator. + * @pfn: PFN of the page we're interested in. + * + * Must be called with RCU read lock taken. + * + * Return: NULL if no page_ext exists for this page. + */ +static inline struct page_ext *page_ext_iter_begin(struct page_ext_iter *iter, + unsigned long pfn) +{ + iter->index = 0; + iter->start_pfn = pfn; + iter->page_ext = page_ext_lookup(pfn); + + return iter->page_ext; +} + +/** + * page_ext_iter_next() - Get next page extension + * @iter: page extension iterator. + * + * Must be called with RCU read lock taken. + * + * Return: NULL if no next page_ext exists. + */ +static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter) +{ + unsigned long pfn; + + if (WARN_ON_ONCE(!iter->page_ext)) + return NULL; + + iter->index++; + pfn = iter->start_pfn + iter->index; + + if (page_ext_iter_next_fast_possible(pfn)) + iter->page_ext = page_ext_next(iter->page_ext); + else + iter->page_ext = page_ext_lookup(pfn); + + return iter->page_ext; +} + +/** + * page_ext_iter_get() - Get current page extension + * @iter: page extension iterator. + * + * Return: NULL if no page_ext exists for this iterator. + */ +static inline struct page_ext *page_ext_iter_get(const struct page_ext_iter *iter) +{ + return iter->page_ext; +} + +/** + * for_each_page_ext(): iterate through page_ext objects. + * @__page: the page we're interested in + * @__pgcount: how many pages to iterate through + * @__page_ext: struct page_ext pointer where the current page_ext + * object is returned + * @__iter: struct page_ext_iter object (defined in the stack) + * + * IMPORTANT: must be called with RCU read lock taken. + */ +#define for_each_page_ext(__page, __pgcount, __page_ext, __iter) \ + for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page));\ + __page_ext && __iter.index < __pgcount; \ + __page_ext = page_ext_iter_next(&__iter)) + #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 8c236c651d1d..544150d1d5fd 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -234,7 +234,7 @@ static inline bool page_ref_add_unless(struct page *page, int nr, int u) rcu_read_lock(); /* avoid writing to the vmemmap area being remapped */ - if (!page_is_fake_head(page) && page_ref_count(page) != u) + if (page_count_writable(page, u)) ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock(); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7661be85136c..26baa78f1ca7 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -536,26 +536,6 @@ struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); /** - * folio_file_mapping - Find the mapping this folio belongs to. - * @folio: The folio. - * - * For folios which are in the page cache, return the mapping that this - * page belongs to. Folios in the swap cache return the mapping of the - * swap file or swap device where the data is stored. This is different - * from the mapping returned by folio_mapping(). The only reason to - * use it is if, like NFS, you return 0 from ->activate_swapfile. - * - * Do not call this for folios which aren't in the page cache or swap cache. - */ -static inline struct address_space *folio_file_mapping(struct folio *folio) -{ - if (unlikely(folio_test_swapcache(folio))) - return swapcache_mapping(folio); - - return folio->mapping; -} - -/** * folio_flush_mapping - Find the file mapping this folio belongs to. * @folio: The folio. * @@ -575,11 +555,6 @@ static inline struct address_space *folio_flush_mapping(struct folio *folio) return folio_mapping(folio); } -static inline struct address_space *page_file_mapping(struct page *page) -{ - return folio_file_mapping(page_folio(page)); -} - /** * folio_inode - Get the host inode for this folio. * @folio: The folio. diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index ac8c44dd8237..c5e9cac0575e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -33,7 +33,7 @@ struct disk_stats { #define part_stat_read(part, field) \ ({ \ - typeof((part)->bd_stats->field) res = 0; \ + TYPEOF_UNQUAL((part)->bd_stats->field) res = 0; \ unsigned int _cpu; \ for_each_possible_cpu(_cpu) \ res += per_cpu_ptr((part)->bd_stats, _cpu)->field; \ diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 0e8b74e63767..75c6c86cf09d 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -42,6 +42,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); +int pci_pasid_status(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ static inline int pci_enable_pasid(struct pci_dev *pdev, int features) { return -EINVAL; } @@ -50,6 +51,8 @@ static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; } static inline int pci_max_pasids(struct pci_dev *pdev) { return -EINVAL; } +static inline int pci_pasid_status(struct pci_dev *pdev) +{ return -EINVAL; } #endif /* CONFIG_PCI_PASID */ #endif /* LINUX_PCI_ATS_H */ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 0fcacb909778..0aeb0e276a3e 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -222,7 +222,7 @@ do { \ } while (0) #define PERCPU_PTR(__p) \ - (typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p)) + (TYPEOF_UNQUAL(*(__p)) __force __kernel *)((__force unsigned long)(__p)) #ifdef CONFIG_SMP @@ -318,7 +318,7 @@ static __always_inline void __this_cpu_preempt_check(const char *op) { } #define __pcpu_size_call_return(stem, variable) \ ({ \ - typeof(variable) pscr_ret__; \ + TYPEOF_UNQUAL(variable) pscr_ret__; \ __verify_pcpu_ptr(&(variable)); \ switch(sizeof(variable)) { \ case 1: pscr_ret__ = stem##1(variable); break; \ @@ -333,7 +333,7 @@ static __always_inline void __this_cpu_preempt_check(const char *op) { } #define __pcpu_size_call_return2(stem, variable, ...) \ ({ \ - typeof(variable) pscr2_ret__; \ + TYPEOF_UNQUAL(variable) pscr2_ret__; \ __verify_pcpu_ptr(&(variable)); \ switch(sizeof(variable)) { \ case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \ diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 3469c4b20105..c74077977830 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -162,74 +162,32 @@ static inline void update_page_tag_ref(union pgtag_ref_handle handle, union code } } -static inline void clear_page_tag_ref(struct page *page) -{ - if (mem_alloc_profiling_enabled()) { - union pgtag_ref_handle handle; - union codetag_ref ref; - - if (get_page_tag_ref(page, &ref, &handle)) { - set_codetag_empty(&ref); - update_page_tag_ref(handle, &ref); - put_page_tag_ref(handle); - } - } -} - -static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, - unsigned int nr) -{ - if (mem_alloc_profiling_enabled()) { - union pgtag_ref_handle handle; - union codetag_ref ref; - - if (get_page_tag_ref(page, &ref, &handle)) { - alloc_tag_add(&ref, task->alloc_tag, PAGE_SIZE * nr); - update_page_tag_ref(handle, &ref); - put_page_tag_ref(handle); - } - } -} +/* Should be called only if mem_alloc_profiling_enabled() */ +void __clear_page_tag_ref(struct page *page); -static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +static inline void clear_page_tag_ref(struct page *page) { - if (mem_alloc_profiling_enabled()) { - union pgtag_ref_handle handle; - union codetag_ref ref; - - if (get_page_tag_ref(page, &ref, &handle)) { - alloc_tag_sub(&ref, PAGE_SIZE * nr); - update_page_tag_ref(handle, &ref); - put_page_tag_ref(handle); - } - } + if (mem_alloc_profiling_enabled()) + __clear_page_tag_ref(page); } -static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline struct alloc_tag *__pgalloc_tag_get(struct page *page) { struct alloc_tag *tag = NULL; - - if (mem_alloc_profiling_enabled()) { - union pgtag_ref_handle handle; - union codetag_ref ref; - - if (get_page_tag_ref(page, &ref, &handle)) { - alloc_tag_sub_check(&ref); - if (ref.ct) - tag = ct_to_alloc_tag(ref.ct); - put_page_tag_ref(handle); - } + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub_check(&ref); + if (ref.ct) + tag = ct_to_alloc_tag(ref.ct); + put_page_tag_ref(handle); } return tag; } -static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) -{ - if (mem_alloc_profiling_enabled() && tag) - this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); -} - void pgalloc_tag_split(struct folio *folio, int old_order, int new_order); void pgalloc_tag_swap(struct folio *new, struct folio *old); @@ -238,11 +196,6 @@ void __init alloc_tag_sec_init(void); #else /* CONFIG_MEM_ALLOC_PROFILING */ static inline void clear_page_tag_ref(struct page *page) {} -static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, - unsigned int nr) {} -static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} -static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } -static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} static inline void alloc_tag_sec_init(void) {} static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {} static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {} diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 4c107e17c547..e2b705c14945 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -222,10 +222,14 @@ static inline int pmd_dirty(pmd_t pmd) * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be - * up to date. This mode can only be entered and left under the protection of - * the page table locks for all page tables which may be modified. In the UP - * case, this is required so that preemption is disabled, and in the SMP case, - * it must synchronize the delayed page table writes properly on other CPUs. + * up to date. + * + * In the general case, no lock is guaranteed to be held between entry and exit + * of the lazy mode. So the implementation must assume preemption may be enabled + * and cpu migration is possible; it must take steps to be robust against this. + * (In practice, for user PTE updates, the appropriate page table lock(s) are + * held, but for kernel PTE updates, no lock is held). Nesting is not permitted + * and the mode cannot be used in interrupt context. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE #define arch_enter_lazy_mmu_mode() do {} while (0) @@ -287,7 +291,6 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, { page_table_check_ptes_set(mm, ptep, pte, nr); - arch_enter_lazy_mmu_mode(); for (;;) { set_pte(ptep, pte); if (--nr == 0) @@ -295,7 +298,6 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, ptep++; pte = pte_next_pfn(pte); } - arch_leave_lazy_mmu_mode(); } #endif #define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 03cd5bae92d3..e63e6e70e860 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -227,8 +227,6 @@ int phy_pm_runtime_get(struct phy *phy); int phy_pm_runtime_get_sync(struct phy *phy); int phy_pm_runtime_put(struct phy *phy); int phy_pm_runtime_put_sync(struct phy *phy); -void phy_pm_runtime_allow(struct phy *phy); -void phy_pm_runtime_forbid(struct phy *phy); int phy_init(struct phy *phy); int phy_exit(struct phy *phy); int phy_power_on(struct phy *phy); @@ -321,16 +319,6 @@ static inline int phy_pm_runtime_put_sync(struct phy *phy) return -ENOSYS; } -static inline void phy_pm_runtime_allow(struct phy *phy) -{ - return; -} - -static inline void phy_pm_runtime_forbid(struct phy *phy) -{ - return; -} - static inline int phy_init(struct phy *phy) { if (!phy) diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index ecf290a0c98f..1f4e4f2b89bb 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5046,6 +5046,7 @@ struct ec_response_pd_status { #define PD_EVENT_DATA_SWAP BIT(3) #define PD_EVENT_TYPEC BIT(4) #define PD_EVENT_PPM BIT(5) +#define PD_EVENT_INIT BIT(6) struct ec_response_host_event_status { uint32_t status; /* PD MCU host event status */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index e2d47eb1a7f3..62d497763e25 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -27,11 +27,16 @@ struct posix_acl_entry { }; struct posix_acl { - refcount_t a_refcount; - unsigned int a_count; - struct rcu_head a_rcu; + /* New members MUST be added within the struct_group() macro below. */ + struct_group_tagged(posix_acl_hdr, hdr, + refcount_t a_refcount; + unsigned int a_count; + struct rcu_head a_rcu; + ); struct posix_acl_entry a_entries[] __counted_by(a_count); }; +static_assert(offsetof(struct posix_acl, a_entries) == sizeof(struct posix_acl_hdr), + "struct member likely outside of struct_group_tagged()"); #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) diff --git a/include/linux/pps_gen_kernel.h b/include/linux/pps_gen_kernel.h index 022ea0ac4440..6214c8aa2e02 100644 --- a/include/linux/pps_gen_kernel.h +++ b/include/linux/pps_gen_kernel.h @@ -43,7 +43,7 @@ struct pps_gen_source_info { /* The main struct */ struct pps_gen_device { - struct pps_gen_source_info info; /* PSS generator info */ + const struct pps_gen_source_info *info; /* PSS generator info */ bool enabled; /* PSS generator status */ unsigned int event; @@ -70,7 +70,7 @@ extern const struct attribute_group *pps_gen_groups[]; */ extern struct pps_gen_device *pps_gen_register_source( - struct pps_gen_source_info *info); + const struct pps_gen_source_info *info); extern void pps_gen_unregister_source(struct pps_gen_device *pps_gen); extern void pps_gen_event(struct pps_gen_device *pps_gen, unsigned int event, void *data); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f8159f8a7d73..120536f4c6eb 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -132,7 +132,7 @@ static inline void rcu_sysrq_end(void) { } #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else -static inline void rcu_irq_work_resched(void) { } +static __always_inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 27343424225c..9ad134a04b41 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -4,18 +4,7 @@ #include <linux/rcupdate.h> #include <linux/sched/signal.h> - -/* - * rcuwait provides a way of blocking and waking up a single - * task in an rcu-safe manner. - * - * The only time @task is non-nil is when a user is blocked (or - * checking if it needs to) on a condition, and reset as soon as we - * know that the condition has succeeded and are awoken. - */ -struct rcuwait { - struct task_struct __rcu *task; -}; +#include <linux/types.h> #define __RCUWAIT_INITIALIZER(name) \ { .task = NULL, } diff --git a/include/linux/reboot.h b/include/linux/reboot.h index abcdde4df697..aa08c3bbbf59 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -177,16 +177,38 @@ void ctrl_alt_del(void); extern void orderly_poweroff(bool force); extern void orderly_reboot(void); -void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown); -static inline void hw_protection_reboot(const char *reason, int ms_until_forced) -{ - __hw_protection_shutdown(reason, ms_until_forced, false); -} +/** + * enum hw_protection_action - Hardware protection action + * + * @HWPROT_ACT_DEFAULT: + * The default action should be taken. This is HWPROT_ACT_SHUTDOWN + * by default, but can be overridden. + * @HWPROT_ACT_SHUTDOWN: + * The system should be shut down (powered off) for HW protection. + * @HWPROT_ACT_REBOOT: + * The system should be rebooted for HW protection. + */ +enum hw_protection_action { HWPROT_ACT_DEFAULT, HWPROT_ACT_SHUTDOWN, HWPROT_ACT_REBOOT }; -static inline void hw_protection_shutdown(const char *reason, int ms_until_forced) +void __hw_protection_trigger(const char *reason, int ms_until_forced, + enum hw_protection_action action); + +/** + * hw_protection_trigger - Trigger default emergency system hardware protection action + * + * @reason: Reason of emergency shutdown or reboot to be printed. + * @ms_until_forced: Time to wait for orderly shutdown or reboot before + * triggering it. Negative value disables the forced + * shutdown or reboot. + * + * Initiate an emergency system shutdown or reboot in order to protect + * hardware from further damage. The exact action taken is controllable at + * runtime and defaults to shutdown. + */ +static inline void hw_protection_trigger(const char *reason, int ms_until_forced) { - __hw_protection_shutdown(reason, ms_until_forced, true); + __hw_protection_trigger(reason, ms_until_forced, HWPROT_ACT_DEFAULT); } /* diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 35f039ecb272..80dc023ac2bf 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -87,6 +87,15 @@ * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * + * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() provide + * acquire and release ordering for cases when the memory occupied by the + * object might be reused to store another object. This is important for the + * cases where secondary validation is required to detect such reuse, e.g. + * SLAB_TYPESAFE_BY_RCU. The secondary validation checks have to happen after + * the refcount is taken, hence acquire order is necessary. Similarly, when the + * object is initialized, all stores to its attributes should be visible before + * the refcount is set, otherwise a stale attribute value might be used by + * another task which succeeds in taking a refcount to the new object. */ #ifndef _LINUX_REFCOUNT_H @@ -126,6 +135,31 @@ static inline void refcount_set(refcount_t *r, int n) } /** + * refcount_set_release - set a refcount's value with release ordering + * @r: the refcount + * @n: value to which the refcount will be set + * + * This function should be used when memory occupied by the object might be + * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. + * + * Provides release memory ordering which will order previous memory operations + * against this store. This ensures all updates to this object are visible + * once the refcount is set and stale values from the object previously + * occupying this memory are overwritten with new ones. + * + * This function should be called only after new object is fully initialized. + * After this call the object should be considered visible to other tasks even + * if it was not yet added into an object collection normally used to discover + * it. This is because other tasks might have discovered the object previously + * occupying the same memory and after memory reuse they can succeed in taking + * refcount to the new object and start using it. + */ +static inline void refcount_set_release(refcount_t *r, int n) +{ + atomic_set_release(&r->refs, n); +} + +/** * refcount_read - get a refcount's value * @r: the refcount * @@ -178,6 +212,71 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) return __refcount_add_not_zero(i, r, NULL); } +static inline __must_check __signed_wrap +bool __refcount_add_not_zero_limited_acquire(int i, refcount_t *r, int *oldp, + int limit) +{ + int old = refcount_read(r); + + do { + if (!old) + break; + + if (i > limit - old) { + if (oldp) + *oldp = old; + return false; + } + } while (!atomic_try_cmpxchg_acquire(&r->refs, &old, old + i)); + + if (oldp) + *oldp = old; + + if (unlikely(old < 0 || old + i < 0)) + refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); + + return old; +} + +static inline __must_check bool +__refcount_inc_not_zero_limited_acquire(refcount_t *r, int *oldp, int limit) +{ + return __refcount_add_not_zero_limited_acquire(1, r, oldp, limit); +} + +static inline __must_check __signed_wrap +bool __refcount_add_not_zero_acquire(int i, refcount_t *r, int *oldp) +{ + return __refcount_add_not_zero_limited_acquire(i, r, oldp, INT_MAX); +} + +/** + * refcount_add_not_zero_acquire - add a value to a refcount with acquire ordering unless it is 0 + * + * @i: the value to add to the refcount + * @r: the refcount + * + * Will saturate at REFCOUNT_SATURATED and WARN. + * + * This function should be used when memory occupied by the object might be + * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. + * + * Provides acquire memory ordering on success, it is assumed the caller has + * guaranteed the object memory to be stable (RCU, etc.). It does provide a + * control dependency and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc_not_zero_acquire() should instead be used to increment a + * reference count. + * + * Return: false if the passed refcount is 0, true otherwise + */ +static inline __must_check bool refcount_add_not_zero_acquire(int i, refcount_t *r) +{ + return __refcount_add_not_zero_acquire(i, r, NULL); +} + static inline __signed_wrap void __refcount_add(int i, refcount_t *r, int *oldp) { @@ -236,6 +335,32 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) return __refcount_inc_not_zero(r, NULL); } +static inline __must_check bool __refcount_inc_not_zero_acquire(refcount_t *r, int *oldp) +{ + return __refcount_add_not_zero_acquire(1, r, oldp); +} + +/** + * refcount_inc_not_zero_acquire - increment a refcount with acquire ordering unless it is 0 + * @r: the refcount to increment + * + * Similar to refcount_inc_not_zero(), but provides acquire memory ordering on + * success. + * + * This function should be used when memory occupied by the object might be + * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. + * + * Provides acquire memory ordering on success, it is assumed the caller has + * guaranteed the object memory to be stable (RCU, etc.). It does provide a + * control dependency and thereby orders future stores. See the comment on top. + * + * Return: true if the increment was successful, false otherwise + */ +static inline __must_check bool refcount_inc_not_zero_acquire(refcount_t *r) +{ + return __refcount_inc_not_zero_acquire(r, NULL); +} + static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 8463a128e2f4..6c85b28ea30b 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1259,7 +1259,7 @@ static inline int rhashtable_replace_fast( static inline void rhltable_walk_enter(struct rhltable *hlt, struct rhashtable_iter *iter) { - return rhashtable_walk_enter(&hlt->ht, iter); + rhashtable_walk_enter(&hlt->ht, iter); } /** @@ -1275,12 +1275,12 @@ static inline void rhltable_free_and_destroy(struct rhltable *hlt, void *arg), void *arg) { - return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); + rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); } static inline void rhltable_destroy(struct rhltable *hlt) { - return rhltable_free_and_destroy(hlt, NULL, NULL); + rhltable_free_and_destroy(hlt, NULL, NULL); } #endif /* _LINUX_RHASHTABLE_H */ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 17fbb7855295..56e27263acf8 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -92,10 +92,10 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flags, int order, unsigned long start, unsigned long range_size, + unsigned long scratch_size, struct lock_class_key *key); -bool ring_buffer_last_boot_delta(struct trace_buffer *buffer, long *text, - long *data); +void *ring_buffer_meta_scratch(struct trace_buffer *buffer, unsigned int *size); /* * Because the ring buffer is generic, if other users of the ring buffer get @@ -113,11 +113,11 @@ bool ring_buffer_last_boot_delta(struct trace_buffer *buffer, long *text, * traced by ftrace, it can produce lockdep warnings. We need to keep each * ring buffer's lock class separate. */ -#define ring_buffer_alloc_range(size, flags, order, start, range_size) \ +#define ring_buffer_alloc_range(size, flags, order, start, range_size, s_size) \ ({ \ static struct lock_class_key __key; \ __ring_buffer_alloc_range((size), (flags), (order), (start), \ - (range_size), &__key); \ + (range_size), (s_size), &__key); \ }) typedef bool (*ring_buffer_cond_fn)(void *data); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 683a04088f3f..6b82b618846e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -13,6 +13,7 @@ #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> +#include <linux/bit_spinlock.h> /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -173,6 +174,214 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *folio_get_anon_vma(const struct folio *folio); +#ifdef CONFIG_MM_ID +static __always_inline void folio_lock_large_mapcount(struct folio *folio) +{ + bit_spin_lock(FOLIO_MM_IDS_LOCK_BITNUM, &folio->_mm_ids); +} + +static __always_inline void folio_unlock_large_mapcount(struct folio *folio) +{ + __bit_spin_unlock(FOLIO_MM_IDS_LOCK_BITNUM, &folio->_mm_ids); +} + +static inline unsigned int folio_mm_id(const struct folio *folio, int idx) +{ + VM_WARN_ON_ONCE(idx != 0 && idx != 1); + return folio->_mm_id[idx] & MM_ID_MASK; +} + +static inline void folio_set_mm_id(struct folio *folio, int idx, mm_id_t id) +{ + VM_WARN_ON_ONCE(idx != 0 && idx != 1); + folio->_mm_id[idx] &= ~MM_ID_MASK; + folio->_mm_id[idx] |= id; +} + +static inline void __folio_large_mapcount_sanity_checks(const struct folio *folio, + int diff, mm_id_t mm_id) +{ + VM_WARN_ON_ONCE(!folio_test_large(folio) || folio_test_hugetlb(folio)); + VM_WARN_ON_ONCE(diff <= 0); + VM_WARN_ON_ONCE(mm_id < MM_ID_MIN || mm_id > MM_ID_MAX); + + /* + * Make sure we can detect at least one complete PTE mapping of the + * folio in a single MM as "exclusively mapped". This is primarily + * a check on 32bit, where we currently reduce the size of the per-MM + * mapcount to a short. + */ + VM_WARN_ON_ONCE(diff > folio_large_nr_pages(folio)); + VM_WARN_ON_ONCE(folio_large_nr_pages(folio) - 1 > MM_ID_MAPCOUNT_MAX); + + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) == MM_ID_DUMMY && + folio->_mm_id_mapcount[0] != -1); + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != MM_ID_DUMMY && + folio->_mm_id_mapcount[0] < 0); + VM_WARN_ON_ONCE(folio_mm_id(folio, 1) == MM_ID_DUMMY && + folio->_mm_id_mapcount[1] != -1); + VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY && + folio->_mm_id_mapcount[1] < 0); + VM_WARN_ON_ONCE(!folio_mapped(folio) && + folio_test_large_maybe_mapped_shared(folio)); +} + +static __always_inline void folio_set_large_mapcount(struct folio *folio, + int mapcount, struct vm_area_struct *vma) +{ + __folio_large_mapcount_sanity_checks(folio, mapcount, vma->vm_mm->mm_id); + + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != MM_ID_DUMMY); + VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY); + + /* Note: mapcounts start at -1. */ + atomic_set(&folio->_large_mapcount, mapcount - 1); + folio->_mm_id_mapcount[0] = mapcount - 1; + folio_set_mm_id(folio, 0, vma->vm_mm->mm_id); +} + +static __always_inline int folio_add_return_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + const mm_id_t mm_id = vma->vm_mm->mm_id; + int new_mapcount_val; + + folio_lock_large_mapcount(folio); + __folio_large_mapcount_sanity_checks(folio, diff, mm_id); + + new_mapcount_val = atomic_read(&folio->_large_mapcount) + diff; + atomic_set(&folio->_large_mapcount, new_mapcount_val); + + /* + * If a folio is mapped more than once into an MM on 32bit, we + * can in theory overflow the per-MM mapcount (although only for + * fairly large folios), turning it negative. In that case, just + * free up the slot and mark the folio "mapped shared", otherwise + * we might be in trouble when unmapping pages later. + */ + if (folio_mm_id(folio, 0) == mm_id) { + folio->_mm_id_mapcount[0] += diff; + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio->_mm_id_mapcount[0] < 0)) { + folio->_mm_id_mapcount[0] = -1; + folio_set_mm_id(folio, 0, MM_ID_DUMMY); + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } + } else if (folio_mm_id(folio, 1) == mm_id) { + folio->_mm_id_mapcount[1] += diff; + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio->_mm_id_mapcount[1] < 0)) { + folio->_mm_id_mapcount[1] = -1; + folio_set_mm_id(folio, 1, MM_ID_DUMMY); + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } + } else if (folio_mm_id(folio, 0) == MM_ID_DUMMY) { + folio_set_mm_id(folio, 0, mm_id); + folio->_mm_id_mapcount[0] = diff - 1; + /* We might have other mappings already. */ + if (new_mapcount_val != diff - 1) + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } else if (folio_mm_id(folio, 1) == MM_ID_DUMMY) { + folio_set_mm_id(folio, 1, mm_id); + folio->_mm_id_mapcount[1] = diff - 1; + /* Slot 0 certainly has mappings as well. */ + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } + folio_unlock_large_mapcount(folio); + return new_mapcount_val + 1; +} +#define folio_add_large_mapcount folio_add_return_large_mapcount + +static __always_inline int folio_sub_return_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + const mm_id_t mm_id = vma->vm_mm->mm_id; + int new_mapcount_val; + + folio_lock_large_mapcount(folio); + __folio_large_mapcount_sanity_checks(folio, diff, mm_id); + + new_mapcount_val = atomic_read(&folio->_large_mapcount) - diff; + atomic_set(&folio->_large_mapcount, new_mapcount_val); + + /* + * There are valid corner cases where we might underflow a per-MM + * mapcount (some mappings added when no slot was free, some mappings + * added once a slot was free), so we always set it to -1 once we go + * negative. + */ + if (folio_mm_id(folio, 0) == mm_id) { + folio->_mm_id_mapcount[0] -= diff; + if (folio->_mm_id_mapcount[0] >= 0) + goto out; + folio->_mm_id_mapcount[0] = -1; + folio_set_mm_id(folio, 0, MM_ID_DUMMY); + } else if (folio_mm_id(folio, 1) == mm_id) { + folio->_mm_id_mapcount[1] -= diff; + if (folio->_mm_id_mapcount[1] >= 0) + goto out; + folio->_mm_id_mapcount[1] = -1; + folio_set_mm_id(folio, 1, MM_ID_DUMMY); + } + + /* + * If one MM slot owns all mappings, the folio is mapped exclusively. + * Note that if the folio is now unmapped (new_mapcount_val == -1), both + * slots must be free (mapcount == -1), and we'll also mark it as + * exclusive. + */ + if (folio->_mm_id_mapcount[0] == new_mapcount_val || + folio->_mm_id_mapcount[1] == new_mapcount_val) + folio->_mm_ids &= ~FOLIO_MM_IDS_SHARED_BIT; +out: + folio_unlock_large_mapcount(folio); + return new_mapcount_val + 1; +} +#define folio_sub_large_mapcount folio_sub_return_large_mapcount +#else /* !CONFIG_MM_ID */ +/* + * See __folio_rmap_sanity_checks(), we might map large folios even without + * CONFIG_TRANSPARENT_HUGEPAGE. We'll keep that working for now. + */ +static inline void folio_set_large_mapcount(struct folio *folio, int mapcount, + struct vm_area_struct *vma) +{ + /* Note: mapcounts start at -1. */ + atomic_set(&folio->_large_mapcount, mapcount - 1); +} + +static inline void folio_add_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + atomic_add(diff, &folio->_large_mapcount); +} + +static inline int folio_add_return_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + BUILD_BUG(); +} + +static inline void folio_sub_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + atomic_sub(diff, &folio->_large_mapcount); +} + +static inline int folio_sub_return_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + BUILD_BUG(); +} +#endif /* CONFIG_MM_ID */ + +#define folio_inc_large_mapcount(folio, vma) \ + folio_add_large_mapcount(folio, 1, vma) +#define folio_inc_return_large_mapcount(folio, vma) \ + folio_add_return_large_mapcount(folio, 1, vma) +#define folio_dec_large_mapcount(folio, vma) \ + folio_sub_large_mapcount(folio, 1, vma) +#define folio_dec_return_large_mapcount(folio, vma) \ + folio_sub_return_large_mapcount(folio, 1, vma) + /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; @@ -192,6 +401,7 @@ typedef int __bitwise rmap_t; enum rmap_level { RMAP_LEVEL_PTE = 0, RMAP_LEVEL_PMD, + RMAP_LEVEL_PUD, }; static inline void __folio_rmap_sanity_checks(const struct folio *folio, @@ -228,6 +438,14 @@ static inline void __folio_rmap_sanity_checks(const struct folio *folio, VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio); VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio); break; + case RMAP_LEVEL_PUD: + /* + * Assume that we are creating a single "entire" mapping of the + * folio. + */ + VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PUD_NR, folio); + VM_WARN_ON_FOLIO(nr_pages != HPAGE_PUD_NR, folio); + break; default: VM_WARN_ON_ONCE(true); } @@ -251,12 +469,16 @@ void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, folio_add_file_rmap_ptes(folio, page, 1, vma) void folio_add_file_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); +void folio_add_file_rmap_pud(struct folio *, struct page *, + struct vm_area_struct *); void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_remove_rmap_pte(folio, page, vma) \ folio_remove_rmap_ptes(folio, page, 1, vma) void folio_remove_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); +void folio_remove_rmap_pud(struct folio *, struct page *, + struct vm_area_struct *); void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); @@ -322,7 +544,8 @@ static inline void hugetlb_remove_rmap(struct folio *folio) } static __always_inline void __folio_dup_file_rmap(struct folio *folio, - struct page *page, int nr_pages, enum rmap_level level) + struct page *page, int nr_pages, struct vm_area_struct *dst_vma, + enum rmap_level level) { const int orig_nr_pages = nr_pages; @@ -335,14 +558,17 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio, break; } - do { - atomic_inc(&page->_mapcount); - } while (page++, --nr_pages > 0); - atomic_add(orig_nr_pages, &folio->_large_mapcount); + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) { + do { + atomic_inc(&page->_mapcount); + } while (page++, --nr_pages > 0); + } + folio_add_large_mapcount(folio, orig_nr_pages, dst_vma); break; case RMAP_LEVEL_PMD: + case RMAP_LEVEL_PUD: atomic_inc(&folio->_entire_mapcount); - atomic_inc(&folio->_large_mapcount); + folio_inc_large_mapcount(folio, dst_vma); break; } } @@ -352,45 +578,47 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio, * @folio: The folio to duplicate the mappings of * @page: The first page to duplicate the mappings of * @nr_pages: The number of pages of which the mapping will be duplicated + * @dst_vma: The destination vm area * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ static inline void folio_dup_file_rmap_ptes(struct folio *folio, - struct page *page, int nr_pages) + struct page *page, int nr_pages, struct vm_area_struct *dst_vma) { - __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); + __folio_dup_file_rmap(folio, page, nr_pages, dst_vma, RMAP_LEVEL_PTE); } static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, - struct page *page) + struct page *page, struct vm_area_struct *dst_vma) { - __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE); + __folio_dup_file_rmap(folio, page, 1, dst_vma, RMAP_LEVEL_PTE); } /** * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio * @folio: The folio to duplicate the mapping of * @page: The first page to duplicate the mapping of + * @dst_vma: The destination vm area * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ static inline void folio_dup_file_rmap_pmd(struct folio *folio, - struct page *page) + struct page *page, struct vm_area_struct *dst_vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PTE); + __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, dst_vma, RMAP_LEVEL_PTE); #else WARN_ON_ONCE(true); #endif } static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, - struct page *page, int nr_pages, struct vm_area_struct *src_vma, - enum rmap_level level) + struct page *page, int nr_pages, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, enum rmap_level level) { const int orig_nr_pages = nr_pages; bool maybe_pinned; @@ -432,18 +660,20 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, do { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); - atomic_inc(&page->_mapcount); + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) + atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); - atomic_add(orig_nr_pages, &folio->_large_mapcount); + folio_add_large_mapcount(folio, orig_nr_pages, dst_vma); break; case RMAP_LEVEL_PMD: + case RMAP_LEVEL_PUD: if (PageAnonExclusive(page)) { if (unlikely(maybe_pinned)) return -EBUSY; ClearPageAnonExclusive(page); } atomic_inc(&folio->_entire_mapcount); - atomic_inc(&folio->_large_mapcount); + folio_inc_large_mapcount(folio, dst_vma); break; } return 0; @@ -455,6 +685,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, * @folio: The folio to duplicate the mappings of * @page: The first page to duplicate the mappings of * @nr_pages: The number of pages of which the mapping will be duplicated + * @dst_vma: The destination vm area * @src_vma: The vm area from which the mappings are duplicated * * The page range of the folio is defined by [page, page + nr_pages) @@ -473,16 +704,18 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise. */ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, - struct page *page, int nr_pages, struct vm_area_struct *src_vma) + struct page *page, int nr_pages, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { - return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, - RMAP_LEVEL_PTE); + return __folio_try_dup_anon_rmap(folio, page, nr_pages, dst_vma, + src_vma, RMAP_LEVEL_PTE); } static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, - struct page *page, struct vm_area_struct *src_vma) + struct page *page, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { - return __folio_try_dup_anon_rmap(folio, page, 1, src_vma, + return __folio_try_dup_anon_rmap(folio, page, 1, dst_vma, src_vma, RMAP_LEVEL_PTE); } @@ -491,6 +724,7 @@ static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, * of a folio * @folio: The folio to duplicate the mapping of * @page: The first page to duplicate the mapping of + * @dst_vma: The destination vm area * @src_vma: The vm area from which the mapping is duplicated * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) @@ -509,11 +743,12 @@ static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. */ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, - struct page *page, struct vm_area_struct *src_vma) + struct page *page, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma, - RMAP_LEVEL_PMD); + return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, dst_vma, + src_vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; @@ -663,9 +898,8 @@ int folio_referenced(struct folio *, int is_locked, void try_to_migrate(struct folio *folio, enum ttu_flags flags); void try_to_unmap(struct folio *, enum ttu_flags flags); -int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, - unsigned long end, struct page **pages, - void *arg); +struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, + void *owner, struct folio **foliop); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) @@ -739,6 +973,9 @@ unsigned long page_address_in_vma(const struct folio *folio, */ int folio_mkclean(struct folio *); +int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff, + unsigned long pfn, unsigned long nr_pages); + int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 3f4d315aaec9..95da051fb155 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -170,6 +170,7 @@ struct rtc_device { /* useful timestamps */ #define RTC_TIMESTAMP_BEGIN_0000 -62167219200ULL /* 0000-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ +#define RTC_TIMESTAMP_EPOCH_GPS 315964800LL /* 1980-01-06 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2079 3471292799LL /* 2079-12-31 23:59:59 */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 56ddeb37b5cd..f96ac1982893 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1239,6 +1239,10 @@ struct task_struct { struct mutex_waiter *blocked_on; #endif +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER + struct mutex *blocker_mutex; +#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index fb1e295e7e63..166b19af956f 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -12,7 +12,7 @@ static __always_inline bool sched_smt_active(void) return static_branch_likely(&sched_smt_present); } #else -static inline bool sched_smt_active(void) { return false; } +static __always_inline bool sched_smt_active(void) { return false; } #endif void arch_smt_update(void); diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index fe41da005970..52791e070506 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -167,8 +167,8 @@ extern int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, const void *buf, size_t len, bool ascii); #ifdef CONFIG_BINARY_PRINTF -extern int -seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); +__printf(2, 0) +int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); #endif void seq_buf_do_printk(struct seq_buf *s, const char *lvl); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 2fb266ea69fa..d6ebf0596510 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -181,6 +181,7 @@ int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); #ifdef CONFIG_BINARY_PRINTF +__printf(2, 0) void seq_bprintf(struct seq_file *m, const char *f, const u32 *binary); #endif diff --git a/include/linux/serdev.h b/include/linux/serdev.h index ff78efc1f60d..34562eb99931 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -84,7 +84,6 @@ enum serdev_parity { struct serdev_controller_ops { ssize_t (*write_buf)(struct serdev_controller *, const u8 *, size_t); void (*write_flush)(struct serdev_controller *); - int (*write_room)(struct serdev_controller *); int (*open)(struct serdev_controller *); void (*close)(struct serdev_controller *); void (*set_flow_control)(struct serdev_controller *, bool); @@ -212,7 +211,6 @@ int serdev_device_break_ctl(struct serdev_device *serdev, int break_state); void serdev_device_write_wakeup(struct serdev_device *); ssize_t serdev_device_write(struct serdev_device *, const u8 *, size_t, long); void serdev_device_write_flush(struct serdev_device *); -int serdev_device_write_room(struct serdev_device *); /* * serdev device driver functions @@ -273,10 +271,6 @@ static inline ssize_t serdev_device_write(struct serdev_device *sdev, return -ENODEV; } static inline void serdev_device_write_flush(struct serdev_device *sdev) {} -static inline int serdev_device_write_room(struct serdev_device *sdev) -{ - return 0; -} #define serdev_device_driver_register(x) #define serdev_device_driver_unregister(x) diff --git a/include/linux/slab.h b/include/linux/slab.h index 98e07e9e9e58..d5a8ab98035c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -137,6 +137,15 @@ enum _slab_flag_bits { * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * + * Note that object identity check has to be done *after* acquiring a + * reference, therefore user has to ensure proper ordering for loads. + * Similarly, when initializing objects allocated with SLAB_TYPESAFE_BY_RCU, + * the newly allocated object has to be fully initialized *before* its + * refcount gets initialized and proper ordering for stores is required. + * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() are + * designed with the proper fences required for reference counting objects + * allocated with SLAB_TYPESAFE_BY_RCU. + * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages @@ -236,12 +245,6 @@ enum _slab_flag_bits { #endif /* - * freeptr_t represents a SLUB freelist pointer, which might be encoded - * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. - */ -typedef struct { unsigned long v; } freeptr_t; - -/* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. diff --git a/include/linux/sort.h b/include/linux/sort.h index e163287ac6c1..8e5603b10941 100644 --- a/include/linux/sort.h +++ b/include/linux/sort.h @@ -13,4 +13,15 @@ void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func); +/* Versions that periodically call cond_resched(): */ + +void sort_r_nonatomic(void *base, size_t num, size_t size, + cmp_r_func_t cmp_func, + swap_r_func_t swap_func, + const void *priv); + +void sort_nonatomic(void *base, size_t num, size_t size, + cmp_func_t cmp_func, + swap_func_t swap_func); + #endif diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 2d6c30317792..2362f621d94c 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -150,12 +150,14 @@ enum sdw_dpn_pkg_mode { * * @SDW_STREAM_PCM: PCM data stream * @SDW_STREAM_PDM: PDM data stream + * @SDW_STREAM_BPT: BPT data stream * * spec doesn't define this, but is used in implementation */ enum sdw_stream_type { SDW_STREAM_PCM = 0, SDW_STREAM_PDM = 1, + SDW_STREAM_BPT = 2, }; /** @@ -822,6 +824,15 @@ struct sdw_defer { struct completion complete; }; +/* + * Add a practical limit to BPT transfer sizes. BPT is typically used + * to transfer firmware, and larger firmware transfers will increase + * the cold latency beyond typical OS or user requirements. + */ +#define SDW_BPT_MSG_MAX_BYTES (1024 * 1024) + +struct sdw_bpt_msg; + /** * struct sdw_master_ops - Master driver ops * @read_prop: Read Master properties @@ -837,6 +848,10 @@ struct sdw_defer { * @get_device_num: Callback for vendor-specific device_number allocation * @put_device_num: Callback for vendor-specific device_number release * @new_peripheral_assigned: Callback to handle enumeration of new peripheral. + * @bpt_send_async: reserve resources for BPT stream and send message + * using BTP protocol + * @bpt_wait: wait for message completion using BTP protocol + * and release resources */ struct sdw_master_ops { int (*read_prop)(struct sdw_bus *bus); @@ -853,6 +868,9 @@ struct sdw_master_ops { void (*new_peripheral_assigned)(struct sdw_bus *bus, struct sdw_slave *slave, int dev_num); + int (*bpt_send_async)(struct sdw_bus *bus, struct sdw_slave *slave, + struct sdw_bpt_msg *msg); + int (*bpt_wait)(struct sdw_bus *bus, struct sdw_slave *slave, struct sdw_bpt_msg *msg); }; int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, @@ -879,7 +897,7 @@ struct sdw_port_config { * @ch_count: Channel count of the stream * @bps: Number of bits per audio sample * @direction: Data direction - * @type: Stream type PCM or PDM + * @type: Stream type PCM, PDM or BPT */ struct sdw_stream_config { unsigned int frame_rate; @@ -929,7 +947,7 @@ struct sdw_stream_params { * @name: SoundWire stream name * @params: Stream parameters * @state: Current state of the stream - * @type: Stream type PCM or PDM + * @type: Stream type PCM, PDM or BPT * @m_rt_count: Count of Master runtime(s) in this stream * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance @@ -959,6 +977,9 @@ struct sdw_stream_runtime { * @defer_msg: Defer message * @params: Current bus parameters * @stream_refcount: number of streams currently using this bus + * @btp_stream_refcount: number of BTP streams currently using this bus (should + * be zero or one, multiple streams per link is not supported). + * @bpt_stream: pointer stored to handle BTP streams. * @ops: Master callback ops * @port_ops: Master port callback ops * @prop: Master properties @@ -996,6 +1017,8 @@ struct sdw_bus { struct sdw_defer defer_msg; struct sdw_bus_params params; int stream_refcount; + int bpt_stream_refcount; + struct sdw_stream_runtime *bpt_stream; const struct sdw_master_ops *ops; const struct sdw_master_port_ops *port_ops; struct sdw_master_prop prop; @@ -1017,7 +1040,7 @@ struct sdw_bus { unsigned int lane_used_bandwidth[SDW_MAX_LANES]; }; -struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name); +struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name, enum sdw_stream_type type); void sdw_release_stream(struct sdw_stream_runtime *stream); int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream); @@ -1043,6 +1066,10 @@ int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave); +int sdw_bpt_send_async(struct sdw_bus *bus, struct sdw_slave *slave, struct sdw_bpt_msg *msg); +int sdw_bpt_wait(struct sdw_bus *bus, struct sdw_slave *slave, struct sdw_bpt_msg *msg); +int sdw_bpt_send_sync(struct sdw_bus *bus, struct sdw_slave *slave, struct sdw_bpt_msg *msg); + #if IS_ENABLED(CONFIG_SOUNDWIRE) int sdw_stream_add_slave(struct sdw_slave *slave, diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index 799f8578137b..6b839987f14c 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -28,6 +28,8 @@ #define ACP_SDW1 1 #define AMD_SDW_MAX_MANAGER_COUNT 2 #define ACP63_PCI_REV_ID 0x63 +#define ACP70_PCI_REV_ID 0x70 +#define ACP71_PCI_REV_ID 0x71 struct acp_sdw_pdata { u16 instance; diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 580086417e4b..493d9de4e472 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -436,6 +436,10 @@ struct sdw_intel_hw_ops { bool (*sync_check_cmdsync_unlocked)(struct sdw_intel *sdw); void (*program_sdi)(struct sdw_intel *sdw, int dev_num); + + int (*bpt_send_async)(struct sdw_intel *sdw, struct sdw_slave *slave, + struct sdw_bpt_msg *msg); + int (*bpt_wait)(struct sdw_intel *sdw, struct sdw_slave *slave, struct sdw_bpt_msg *msg); }; extern const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops; diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h index 33dcbec71925..51cab2def9ec 100644 --- a/include/linux/sprintf.h +++ b/include/linux/sprintf.h @@ -24,4 +24,7 @@ __scanf(2, 0) int vsscanf(const char *, const char *, va_list); extern bool no_hash_pointers; int no_hash_pointers_enable(char *str); +/* Used for Rust formatting ('%pA') */ +char *rust_fmt_argument(char *buf, char *end, const void *ptr); + #endif /* _LINUX_KERNEL_SPRINTF_H */ diff --git a/include/linux/string.h b/include/linux/string.h index 0403a4ca4c11..01621ad0f598 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -336,8 +336,8 @@ int __sysfs_match_string(const char * const *array, size_t n, const char *s); #define sysfs_match_string(_a, _s) __sysfs_match_string(_a, ARRAY_SIZE(_a), _s) #ifdef CONFIG_BINARY_PRINTF -int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); -int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); +__printf(3, 0) int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); +__printf(3, 0) int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index fec976e58174..f8b406b0a1af 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -64,7 +64,9 @@ struct rpc_clnt { cl_noretranstimeo: 1,/* No retransmit timeouts */ cl_autobind : 1,/* use getport() */ cl_chatty : 1,/* be verbose */ - cl_shutdown : 1;/* rpc immediate -EIO */ + cl_shutdown : 1,/* rpc immediate -EIO */ + cl_netunreach_fatal : 1; + /* Treat ENETUNREACH errors as fatal */ struct xprtsec_parms cl_xprtsec; /* transport security policy */ struct rpc_rtt * cl_rtt; /* RTO estimator data */ @@ -175,6 +177,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) #define RPC_CLNT_CREATE_CONNECTED (1UL << 12) +#define RPC_CLNT_CREATE_NETUNREACH_FATAL (1UL << 13) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index eac57914dcf3..ccba79ebf893 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -134,6 +134,7 @@ struct rpc_task_setup { #define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ +#define RPC_TASK_NETUNREACH_FATAL 0x0040 /* ENETUNREACH is fatal */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ #define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index e411368cdacf..e4db5022fe92 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -56,6 +56,7 @@ extern void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt); extern void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, bool offline); +extern struct rpc_xprt *rpc_xprt_switch_get_main_xprt(struct rpc_xprt_switch *xps); extern void xprt_iter_init(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps); diff --git a/include/linux/swap.h b/include/linux/swap.h index a98c757400fe..db46b25a65ae 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -24,7 +24,6 @@ struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff -#define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ @@ -74,14 +73,13 @@ static inline int current_is_kswapd(void) * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page - * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. + * table entries to a special SWP_DEVICE_EXCLUSIVE entry. */ #ifdef CONFIG_DEVICE_PRIVATE -#define SWP_DEVICE_NUM 4 +#define SWP_DEVICE_NUM 3 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) -#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) -#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) +#define SWP_DEVICE_EXCLUSIVE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #else #define SWP_DEVICE_NUM 0 #endif @@ -286,12 +284,10 @@ enum swap_cluster_flags { #endif /* - * We assign a cluster to each CPU, so each CPU can allocate swap entry from - * its own cluster and swapout sequentially. The purpose is to optimize swapout - * throughput. + * We keep using same cluster for rotational device so IO will be sequential. + * The purpose is to optimize SWAP throughput on these device. */ -struct percpu_cluster { - local_lock_t lock; /* Protect the percpu_cluster above */ +struct swap_sequential_cluster { unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; @@ -317,8 +313,7 @@ struct swap_info_struct { atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int pages; /* total of usable pages of swap */ atomic_long_t inuse_pages; /* number of those currently in use */ - struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ - struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */ + struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */ spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ @@ -461,7 +456,6 @@ void free_pages_and_swap_cache(struct encoded_page **, int); extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; -extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) @@ -475,24 +469,22 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -swp_entry_t folio_alloc_swap(struct folio *folio); +int folio_alloc_swap(struct folio *folio, gfp_t gfp_mask); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); -extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); -extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); +extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; @@ -575,9 +567,9 @@ static inline int __swap_count(swp_entry_t entry) return 0; } -static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) +static inline bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { - return 0; + return false; } static inline int swp_swapcount(swp_entry_t entry) @@ -585,11 +577,9 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -static inline swp_entry_t folio_alloc_swap(struct folio *folio) +static inline int folio_alloc_swap(struct folio *folio, gfp_t gfp_mask) { - swp_entry_t entry; - entry.val = 0; - return entry; + return -EINVAL; } static inline bool folio_free_swap(struct folio *folio) @@ -650,7 +640,6 @@ static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) -void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) @@ -671,10 +660,6 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else -static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) -{ -} - static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h deleted file mode 100644 index 840aec3523b2..000000000000 --- a/include/linux/swap_slots.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_SWAP_SLOTS_H -#define _LINUX_SWAP_SLOTS_H - -#include <linux/swap.h> -#include <linux/spinlock.h> -#include <linux/mutex.h> - -#define SWAP_SLOTS_CACHE_SIZE SWAP_BATCH -#define THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE (5*SWAP_SLOTS_CACHE_SIZE) -#define THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE (2*SWAP_SLOTS_CACHE_SIZE) - -struct swap_slots_cache { - bool lock_initialized; - struct mutex alloc_lock; /* protects slots, nr, cur */ - swp_entry_t *slots; - int nr; - int cur; - int n_ret; -}; - -void disable_swap_slots_cache_lock(void); -void reenable_swap_slots_cache_unlock(void); -void enable_swap_slots_cache(void); - -extern bool swap_slot_cache_enabled; - -#endif /* _LINUX_SWAP_SLOTS_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 96f26e29fefe..64ea151a7ae3 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -186,26 +186,16 @@ static inline bool is_writable_device_private_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } -static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) +static inline swp_entry_t make_device_exclusive_entry(pgoff_t offset) { - return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); -} - -static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) -{ - return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); + return swp_entry(SWP_DEVICE_EXCLUSIVE, offset); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { - return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || - swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; + return swp_type(entry) == SWP_DEVICE_EXCLUSIVE; } -static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) -{ - return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); -} #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { @@ -227,12 +217,7 @@ static inline bool is_writable_device_private_entry(swp_entry_t entry) return false; } -static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) -{ - return swp_entry(0, 0); -} - -static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) +static inline swp_entry_t make_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } @@ -242,10 +227,6 @@ static inline bool is_device_exclusive_entry(swp_entry_t entry) return false; } -static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) -{ - return false; -} #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 69f9bedd0ee8..0b5ed6821080 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -86,8 +86,6 @@ struct thermal_trip { #define THERMAL_TRIP_PRIV_TO_INT(_val_) (uintptr_t)(_val_) #define THERMAL_INT_TO_TRIP_PRIV(_val_) (void *)(uintptr_t)(_val_) -struct thermal_zone_device; - struct cooling_spec { unsigned long upper; /* Highest cooling state */ unsigned long lower; /* Lowest cooling state */ diff --git a/include/linux/timer.h b/include/linux/timer.h index e67ecd1cbc97..10596d7c3a34 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -30,7 +30,7 @@ * * @TIMER_IRQSAFE: An irqsafe timer is executed with IRQ disabled and * it's safe to wait for the completion of the running instance from - * IRQ handlers, for example, by calling del_timer_sync(). + * IRQ handlers, for example, by calling timer_delete_sync(). * * Note: The irq disabled callback execution is a special case for * workqueue locking issues. It's not meant for executing random crap @@ -168,40 +168,6 @@ extern int timer_delete(struct timer_list *timer); extern int timer_shutdown_sync(struct timer_list *timer); extern int timer_shutdown(struct timer_list *timer); -/** - * del_timer_sync - Delete a pending timer and wait for a running callback - * @timer: The timer to be deleted - * - * See timer_delete_sync() for detailed explanation. - * - * Do not use in new code. Use timer_delete_sync() instead. - * - * Returns: - * * %0 - The timer was not pending - * * %1 - The timer was pending and deactivated - */ -static inline int del_timer_sync(struct timer_list *timer) -{ - return timer_delete_sync(timer); -} - -/** - * del_timer - Delete a pending timer - * @timer: The timer to be deleted - * - * See timer_delete() for detailed explanation. - * - * Do not use in new code. Use timer_delete() instead. - * - * Returns: - * * %0 - The timer was not pending - * * %1 - The timer was pending and deactivated - */ -static inline int del_timer(struct timer_list *timer) -{ - return timer_delete(timer); -} - extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); diff --git a/include/linux/trace.h b/include/linux/trace.h index fdcd76b7be83..7eaad857dee0 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -72,8 +72,8 @@ static inline int unregister_ftrace_export(struct trace_export *export) static inline void trace_printk_init_buffers(void) { } -static inline int trace_array_printk(struct trace_array *tr, unsigned long ip, - const char *fmt, ...) +static inline __printf(3, 4) +int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { return 0; } diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 1ef95c0287f0..a93ed5ac3226 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -88,8 +88,8 @@ extern __printf(2, 3) void trace_seq_printf(struct trace_seq *s, const char *fmt, ...); extern __printf(2, 0) void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args); -extern void -trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); +extern __printf(2, 0) +void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); extern int trace_print_seq(struct seq_file *m, struct trace_seq *s); extern int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt); @@ -113,8 +113,8 @@ static inline __printf(2, 3) void trace_seq_printf(struct trace_seq *s, const char *fmt, ...) { } -static inline void -trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) +static inline __printf(2, 0) +void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) { } diff --git a/include/linux/tty.h b/include/linux/tty.h index 2372f9357240..0a46e4054dec 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -239,7 +239,6 @@ struct tty_struct { struct list_head tty_files; -#define N_TTY_BUF_SIZE 4096 struct work_struct SAK_work; } __randomize_layout; @@ -251,7 +250,7 @@ struct tty_file_private { }; /** - * DOC: TTY Struct Flags + * enum tty_struct_flags - TTY Struct Flags * * These bits are used in the :c:member:`tty_struct.flags` field. * @@ -260,62 +259,64 @@ struct tty_file_private { * tty->write. Thus, you must use the inline functions set_bit() and * clear_bit() to make things atomic. * - * TTY_THROTTLED + * @TTY_THROTTLED: * Driver input is throttled. The ldisc should call * :c:member:`tty_driver.unthrottle()` in order to resume reception when * it is ready to process more data (at threshold min). * - * TTY_IO_ERROR + * @TTY_IO_ERROR: * If set, causes all subsequent userspace read/write calls on the tty to * fail, returning -%EIO. (May be no ldisc too.) * - * TTY_OTHER_CLOSED + * @TTY_OTHER_CLOSED: * Device is a pty and the other side has closed. * - * TTY_EXCLUSIVE + * @TTY_EXCLUSIVE: * Exclusive open mode (a single opener). * - * TTY_DO_WRITE_WAKEUP + * @TTY_DO_WRITE_WAKEUP: * If set, causes the driver to call the * :c:member:`tty_ldisc_ops.write_wakeup()` method in order to resume * transmission when it can accept more data to transmit. * - * TTY_LDISC_OPEN + * @TTY_LDISC_OPEN: * Indicates that a line discipline is open. For debugging purposes only. * - * TTY_PTY_LOCK + * @TTY_PTY_LOCK: * A flag private to pty code to implement %TIOCSPTLCK/%TIOCGPTLCK logic. * - * TTY_NO_WRITE_SPLIT + * @TTY_NO_WRITE_SPLIT: * Prevent driver from splitting up writes into smaller chunks (preserve * write boundaries to driver). * - * TTY_HUPPED + * @TTY_HUPPED: * The TTY was hung up. This is set post :c:member:`tty_driver.hangup()`. * - * TTY_HUPPING + * @TTY_HUPPING: * The TTY is in the process of hanging up to abort potential readers. * - * TTY_LDISC_CHANGING + * @TTY_LDISC_CHANGING: * Line discipline for this TTY is being changed. I/O should not block * when this is set. Use tty_io_nonblock() to check. * - * TTY_LDISC_HALTED + * @TTY_LDISC_HALTED: * Line discipline for this TTY was stopped. No work should be queued to * this ldisc. */ -#define TTY_THROTTLED 0 -#define TTY_IO_ERROR 1 -#define TTY_OTHER_CLOSED 2 -#define TTY_EXCLUSIVE 3 -#define TTY_DO_WRITE_WAKEUP 5 -#define TTY_LDISC_OPEN 11 -#define TTY_PTY_LOCK 16 -#define TTY_NO_WRITE_SPLIT 17 -#define TTY_HUPPED 18 -#define TTY_HUPPING 19 -#define TTY_LDISC_CHANGING 20 -#define TTY_LDISC_HALTED 22 +enum tty_struct_flags { + TTY_THROTTLED, + TTY_IO_ERROR, + TTY_OTHER_CLOSED, + TTY_EXCLUSIVE, + TTY_DO_WRITE_WAKEUP, + TTY_LDISC_OPEN, + TTY_PTY_LOCK, + TTY_NO_WRITE_SPLIT, + TTY_HUPPED, + TTY_HUPPING, + TTY_LDISC_CHANGING, + TTY_LDISC_HALTED, +}; static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) { diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index d4cdc089f6c3..188ee9b768eb 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -17,6 +17,92 @@ struct serial_icounter_struct; struct serial_struct; /** + * enum tty_driver_flag -- TTY Driver Flags + * + * These are flags passed to tty_alloc_driver(). + * + * @TTY_DRIVER_INSTALLED: + * Whether this driver was succesfully installed. This is a tty internal + * flag. Do not touch. + * + * @TTY_DRIVER_RESET_TERMIOS: + * Requests the tty layer to reset the termios setting when the last + * process has closed the device. Used for PTYs, in particular. + * + * @TTY_DRIVER_REAL_RAW: + * Indicates that the driver will guarantee not to set any special + * character handling flags if this is set for the tty: + * + * ``(IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || !INPCK)`` + * + * That is, if there is no reason for the driver to + * send notifications of parity and break characters up to the line + * driver, it won't do so. This allows the line driver to optimize for + * this case if this flag is set. (Note that there is also a promise, if + * the above case is true, not to signal overruns, either.) + * + * @TTY_DRIVER_DYNAMIC_DEV: + * The individual tty devices need to be registered with a call to + * tty_register_device() when the device is found in the system and + * unregistered with a call to tty_unregister_device() so the devices will + * be show up properly in sysfs. If not set, all &tty_driver.num entries + * will be created by the tty core in sysfs when tty_register_driver() is + * called. This is to be used by drivers that have tty devices that can + * appear and disappear while the main tty driver is registered with the + * tty core. + * + * @TTY_DRIVER_DEVPTS_MEM: + * Don't use the standard arrays (&tty_driver.ttys and + * &tty_driver.termios), instead use dynamic memory keyed through the + * devpts filesystem. This is only applicable to the PTY driver. + * + * @TTY_DRIVER_HARDWARE_BREAK: + * Hardware handles break signals. Pass the requested timeout to the + * &tty_operations.break_ctl instead of using a simple on/off interface. + * + * @TTY_DRIVER_DYNAMIC_ALLOC: + * Do not allocate structures which are needed per line for this driver + * (&tty_driver.ports) as it would waste memory. The driver will take + * care. This is only applicable to the PTY driver. + * + * @TTY_DRIVER_UNNUMBERED_NODE: + * Do not create numbered ``/dev`` nodes. For example, create + * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a + * driver for a single tty device is being allocated. + */ +enum tty_driver_flag { + TTY_DRIVER_INSTALLED = BIT(0), + TTY_DRIVER_RESET_TERMIOS = BIT(1), + TTY_DRIVER_REAL_RAW = BIT(2), + TTY_DRIVER_DYNAMIC_DEV = BIT(3), + TTY_DRIVER_DEVPTS_MEM = BIT(4), + TTY_DRIVER_HARDWARE_BREAK = BIT(5), + TTY_DRIVER_DYNAMIC_ALLOC = BIT(6), + TTY_DRIVER_UNNUMBERED_NODE = BIT(7), +}; + +enum tty_driver_type { + TTY_DRIVER_TYPE_SYSTEM, + TTY_DRIVER_TYPE_CONSOLE, + TTY_DRIVER_TYPE_SERIAL, + TTY_DRIVER_TYPE_PTY, + TTY_DRIVER_TYPE_SCC, + TTY_DRIVER_TYPE_SYSCONS, +}; + +enum tty_driver_subtype { + SYSTEM_TYPE_TTY = 1, + SYSTEM_TYPE_CONSOLE, + SYSTEM_TYPE_SYSCONS, + SYSTEM_TYPE_SYSPTMX, + + PTY_TYPE_MASTER = 1, + PTY_TYPE_SLAVE, + + SERIAL_TYPE_NORMAL = 1, +}; + +/** * struct tty_operations -- interface between driver and tty * * @lookup: ``struct tty_struct *()(struct tty_driver *self, struct file *, @@ -414,8 +500,8 @@ struct tty_operations { * @major: major /dev device number (zero for autoassignment) * @minor_start: the first minor /dev device number * @num: number of devices allocated - * @type: type of tty driver (%TTY_DRIVER_TYPE_) - * @subtype: subtype of tty driver (%SYSTEM_TYPE_, %PTY_TYPE_, %SERIAL_TYPE_) + * @type: type of tty driver (enum tty_driver_type) + * @subtype: subtype of tty driver (enum tty_driver_subtype) * @init_termios: termios to set to each tty initially (e.g. %tty_std_termios) * @flags: tty driver flags (%TTY_DRIVER_) * @proc_entry: proc fs entry, used internally @@ -447,8 +533,8 @@ struct tty_driver { int major; int minor_start; unsigned int num; - short type; - short subtype; + enum tty_driver_type type; + enum tty_driver_subtype subtype; struct ktermios init_termios; unsigned long flags; struct proc_dir_entry *proc_entry; @@ -478,7 +564,13 @@ struct tty_driver *tty_find_polling_driver(char *name, int *line); void tty_driver_kref_put(struct tty_driver *driver); -/* Use TTY_DRIVER_* flags below */ +/** + * tty_alloc_driver - allocate tty driver + * @lines: count of lines this driver can handle at most + * @flags: some of enum tty_driver_flag, will be set in driver->flags + * + * Returns: struct tty_driver or a PTR-encoded error (use IS_ERR() and friends). + */ #define tty_alloc_driver(lines, flags) \ __tty_alloc_driver(lines, THIS_MODULE, flags) @@ -494,84 +586,6 @@ static inline void tty_set_operations(struct tty_driver *driver, driver->ops = op; } -/** - * DOC: TTY Driver Flags - * - * TTY_DRIVER_RESET_TERMIOS - * Requests the tty layer to reset the termios setting when the last - * process has closed the device. Used for PTYs, in particular. - * - * TTY_DRIVER_REAL_RAW - * Indicates that the driver will guarantee not to set any special - * character handling flags if this is set for the tty: - * - * ``(IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || !INPCK)`` - * - * That is, if there is no reason for the driver to - * send notifications of parity and break characters up to the line - * driver, it won't do so. This allows the line driver to optimize for - * this case if this flag is set. (Note that there is also a promise, if - * the above case is true, not to signal overruns, either.) - * - * TTY_DRIVER_DYNAMIC_DEV - * The individual tty devices need to be registered with a call to - * tty_register_device() when the device is found in the system and - * unregistered with a call to tty_unregister_device() so the devices will - * be show up properly in sysfs. If not set, all &tty_driver.num entries - * will be created by the tty core in sysfs when tty_register_driver() is - * called. This is to be used by drivers that have tty devices that can - * appear and disappear while the main tty driver is registered with the - * tty core. - * - * TTY_DRIVER_DEVPTS_MEM - * Don't use the standard arrays (&tty_driver.ttys and - * &tty_driver.termios), instead use dynamic memory keyed through the - * devpts filesystem. This is only applicable to the PTY driver. - * - * TTY_DRIVER_HARDWARE_BREAK - * Hardware handles break signals. Pass the requested timeout to the - * &tty_operations.break_ctl instead of using a simple on/off interface. - * - * TTY_DRIVER_DYNAMIC_ALLOC - * Do not allocate structures which are needed per line for this driver - * (&tty_driver.ports) as it would waste memory. The driver will take - * care. This is only applicable to the PTY driver. - * - * TTY_DRIVER_UNNUMBERED_NODE - * Do not create numbered ``/dev`` nodes. For example, create - * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a - * driver for a single tty device is being allocated. - */ -#define TTY_DRIVER_INSTALLED 0x0001 -#define TTY_DRIVER_RESET_TERMIOS 0x0002 -#define TTY_DRIVER_REAL_RAW 0x0004 -#define TTY_DRIVER_DYNAMIC_DEV 0x0008 -#define TTY_DRIVER_DEVPTS_MEM 0x0010 -#define TTY_DRIVER_HARDWARE_BREAK 0x0020 -#define TTY_DRIVER_DYNAMIC_ALLOC 0x0040 -#define TTY_DRIVER_UNNUMBERED_NODE 0x0080 - -/* tty driver types */ -#define TTY_DRIVER_TYPE_SYSTEM 0x0001 -#define TTY_DRIVER_TYPE_CONSOLE 0x0002 -#define TTY_DRIVER_TYPE_SERIAL 0x0003 -#define TTY_DRIVER_TYPE_PTY 0x0004 -#define TTY_DRIVER_TYPE_SCC 0x0005 /* scc driver */ -#define TTY_DRIVER_TYPE_SYSCONS 0x0006 - -/* system subtypes (magic, used by tty_io.c) */ -#define SYSTEM_TYPE_TTY 0x0001 -#define SYSTEM_TYPE_CONSOLE 0x0002 -#define SYSTEM_TYPE_SYSCONS 0x0003 -#define SYSTEM_TYPE_SYSPTMX 0x0004 - -/* pty subtypes (magic, used by tty_io.c) */ -#define PTY_TYPE_MASTER 0x0001 -#define PTY_TYPE_SLAVE 0x0002 - -/* serial subtype definitions */ -#define SERIAL_TYPE_NORMAL 1 - int tty_register_driver(struct tty_driver *driver); void tty_unregister_driver(struct tty_driver *driver); struct device *tty_register_device(struct tty_driver *driver, unsigned index, diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index af01e89074b2..c5cccc3fc1e8 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -39,7 +39,6 @@ do { \ int ldsem_down_read(struct ld_semaphore *sem, long timeout); int ldsem_down_read_trylock(struct ld_semaphore *sem); int ldsem_down_write(struct ld_semaphore *sem, long timeout); -int ldsem_down_write_trylock(struct ld_semaphore *sem); void ldsem_up_read(struct ld_semaphore *sem); void ldsem_up_write(struct ld_semaphore *sem); diff --git a/include/linux/types.h b/include/linux/types.h index 1c509ce8f7f6..49b79c8bb1a9 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -92,6 +92,7 @@ typedef unsigned char unchar; typedef unsigned short ushort; typedef unsigned int uint; typedef unsigned long ulong; +typedef unsigned long long ullong; #ifndef __BIT_TYPES_DEFINED__ #define __BIT_TYPES_DEFINED__ @@ -248,5 +249,17 @@ typedef void (*swap_func_t)(void *a, void *b, int size); typedef int (*cmp_r_func_t)(const void *a, const void *b, const void *priv); typedef int (*cmp_func_t)(const void *a, const void *b); +/* + * rcuwait provides a way of blocking and waking up a single + * task in an rcu-safe manner. + * + * The only time @task is non-nil is when a user is blocked (or + * checking if it needs to) on a condition, and reset as soon as we + * know that the condition has succeeded and are awoken. + */ +struct rcuwait { + struct task_struct __rcu *task; +}; + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_TYPES_H */ diff --git a/include/linux/usb.h b/include/linux/usb.h index cfa8005e24f9..b46738701f8d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -51,6 +51,7 @@ struct ep_device; * @desc: descriptor for this endpoint, wMaxPacketSize in native byteorder * @ss_ep_comp: SuperSpeed companion descriptor for this endpoint * @ssp_isoc_ep_comp: SuperSpeedPlus isoc companion descriptor for this endpoint + * @eusb2_isoc_ep_comp: eUSB2 isoc companion descriptor for this endpoint * @urb_list: urbs queued to this endpoint; maintained by usbcore * @hcpriv: for use by HCD; typically holds hardware dma queue head (QH) * with one or more transfer descriptors (TDs) per urb @@ -64,9 +65,10 @@ struct ep_device; * descriptor within an active interface in a given USB configuration. */ struct usb_host_endpoint { - struct usb_endpoint_descriptor desc; - struct usb_ss_ep_comp_descriptor ss_ep_comp; - struct usb_ssp_isoc_ep_comp_descriptor ssp_isoc_ep_comp; + struct usb_endpoint_descriptor desc; + struct usb_ss_ep_comp_descriptor ss_ep_comp; + struct usb_ssp_isoc_ep_comp_descriptor ssp_isoc_ep_comp; + struct usb_eusb2_isoc_ep_comp_descriptor eusb2_isoc_ep_comp; struct list_head urb_list; void *hcpriv; struct ep_device *ep_dev; /* For sysfs info */ diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 3963e55e88a3..fbdef950f06c 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -61,7 +61,7 @@ struct musb_hdrc_eps_bits { }; struct musb_hdrc_config { - struct musb_fifo_cfg *fifo_cfg; /* board fifo configuration */ + const struct musb_fifo_cfg *fifo_cfg; /* board fifo configuration */ unsigned fifo_cfg_size; /* size of the fifo configuration */ /* MUSB configuration-specific details */ diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index 5050f502c1ed..4b651065738a 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -49,19 +49,10 @@ /*-------------------------------------------------------------------------*/ #if IS_ENABLED(CONFIG_USB_ULPI) -struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, - unsigned int flags); - struct usb_phy *devm_otg_ulpi_create(struct device *dev, struct usb_phy_io_ops *ops, unsigned int flags); #else -static inline struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, - unsigned int flags) -{ - return NULL; -} - static inline struct usb_phy *devm_otg_ulpi_create(struct device *dev, struct usb_phy_io_ops *ops, unsigned int flags) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 7183e5aca282..a0bb6d012137 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -5,8 +5,10 @@ #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> +#include <linux/rculist_nulls.h> #include <linux/sched.h> #include <linux/workqueue.h> +#include <linux/rcuref.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> @@ -115,10 +117,11 @@ struct user_namespace { } __randomize_layout; struct ucounts { - struct hlist_node node; + struct hlist_nulls_node node; struct user_namespace *ns; kuid_t uid; - atomic_t count; + struct rcu_head rcu; + rcuref_t count; atomic_long_t ucount[UCOUNT_COUNTS]; atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; @@ -131,9 +134,15 @@ void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); -struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); +static inline struct ucounts * __must_check get_ucounts(struct ucounts *ucounts) +{ + if (rcuref_get(&ucounts->count)) + return ucounts; + return NULL; +} + static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { return atomic_long_read(&ucounts->rlimit[type]); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 000a6cab2d31..707b00772ce1 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -67,6 +67,7 @@ struct vfio_device { struct inode *inode; #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; + struct ida pasids; u8 iommufd_attached:1; #endif u8 cdev_opened:1; @@ -91,6 +92,8 @@ struct vfio_device { * bound iommufd. Undo in unbind_iommufd if @detach_ioas is not * called. * @detach_ioas: Opposite of attach_ioas + * @pasid_attach_ioas: The pasid variation of attach_ioas + * @pasid_detach_ioas: Opposite of pasid_attach_ioas * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device * @read: Perform read(2) on device file descriptor @@ -115,6 +118,9 @@ struct vfio_device_ops { void (*unbind_iommufd)(struct vfio_device *vdev); int (*attach_ioas)(struct vfio_device *vdev, u32 *pt_id); void (*detach_ioas)(struct vfio_device *vdev); + int (*pasid_attach_ioas)(struct vfio_device *vdev, u32 pasid, + u32 *pt_id); + void (*pasid_detach_ioas)(struct vfio_device *vdev, u32 pasid); int (*open_device)(struct vfio_device *vdev); void (*close_device)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, @@ -139,6 +145,10 @@ int vfio_iommufd_physical_bind(struct vfio_device *vdev, void vfio_iommufd_physical_unbind(struct vfio_device *vdev); int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id); void vfio_iommufd_physical_detach_ioas(struct vfio_device *vdev); +int vfio_iommufd_physical_pasid_attach_ioas(struct vfio_device *vdev, + u32 pasid, u32 *pt_id); +void vfio_iommufd_physical_pasid_detach_ioas(struct vfio_device *vdev, + u32 pasid); int vfio_iommufd_emulated_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx, u32 *out_device_id); void vfio_iommufd_emulated_unbind(struct vfio_device *vdev); @@ -166,6 +176,10 @@ vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx) ((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL) #define vfio_iommufd_physical_detach_ioas \ ((void (*)(struct vfio_device *vdev)) NULL) +#define vfio_iommufd_physical_pasid_attach_ioas \ + ((int (*)(struct vfio_device *vdev, u32 pasid, u32 *pt_id)) NULL) +#define vfio_iommufd_physical_pasid_detach_ioas \ + ((void (*)(struct vfio_device *vdev, u32 pasid)) NULL) #define vfio_iommufd_emulated_bind \ ((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx, \ u32 *out_device_id)) NULL) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5a37cb2b6f93..9e15a088ba38 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -41,9 +41,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSTEAL_KHUGEPAGED, + PGSTEAL_PROACTIVE, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_KHUGEPAGED, + PGSCAN_PROACTIVE, PGSCAN_DIRECT_THROTTLE, PGSCAN_ANON, PGSCAN_FILE, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 4751e3ecc467..b2ccb6845595 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -504,7 +504,7 @@ static inline const char *node_stat_name(enum node_stat_item item) static inline const char *lru_list_name(enum lru_list lru) { - return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" + return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index caf4f0b12235..eda4b62511f7 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -313,6 +313,30 @@ static inline void cgroup_writeback_umount(struct super_block *sb) /* * mm/page-writeback.c */ +/* consolidated parameters for balance_dirty_pages() and its subroutines */ +struct dirty_throttle_control { +#ifdef CONFIG_CGROUP_WRITEBACK + struct wb_domain *dom; + struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ +#endif + struct bdi_writeback *wb; + struct fprop_local_percpu *wb_completions; + + unsigned long avail; /* dirtyable */ + unsigned long dirty; /* file_dirty + write + nfs */ + unsigned long thresh; /* dirty threshold */ + unsigned long bg_thresh; /* dirty background threshold */ + unsigned long limit; /* hard dirty limit */ + + unsigned long wb_dirty; /* per-wb counterparts */ + unsigned long wb_thresh; + unsigned long wb_bg_thresh; + + unsigned long pos_ratio; + bool freerun; + bool dirty_exceeded; +}; + void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); void laptop_mode_timer_fn(struct timer_list *t); diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 0b618ec04115..78eede109b1a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1555,6 +1555,8 @@ int xa_get_order(struct xarray *, unsigned long index); int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); +void xas_try_split(struct xa_state *xas, void *entry, unsigned int order); +unsigned int xas_try_split_min_order(unsigned int order); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { @@ -1576,6 +1578,17 @@ static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } + +static inline void xas_try_split(struct xa_state *xas, void *entry, + unsigned int order) +{ +} + +static inline unsigned int xas_try_split_min_order(unsigned int order) +{ + return 0; +} + #endif /** diff --git a/include/linux/zpool.h b/include/linux/zpool.h index a67d62b79698..52f30e526607 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -4,9 +4,8 @@ * * Copyright (C) 2014 Dan Streetman * - * This is a common frontend for the zbud and zsmalloc memory - * storage pool implementations. Typically, this is used to - * store compressed memory. + * This is a common frontend for the zswap compressed memory storage + * implementations. */ #ifndef _ZPOOL_H_ @@ -14,25 +13,6 @@ struct zpool; -/* - * Control how a handle is mapped. It will be ignored if the - * implementation does not support it. Its use is optional. - * Note that this does not refer to memory protection, it - * refers to how the memory will be copied in/out if copying - * is necessary during mapping; read-write is the safest as - * it copies the existing memory in on map, and copies the - * changed memory back out on unmap. Write-only does not copy - * in the memory and should only be used for initialization. - * If in doubt, use ZPOOL_MM_DEFAULT which is read-write. - */ -enum zpool_mapmode { - ZPOOL_MM_RW, /* normal read-write mapping */ - ZPOOL_MM_RO, /* read-only (no copy-out at unmap time) */ - ZPOOL_MM_WO, /* write-only (no copy-in at map time) */ - - ZPOOL_MM_DEFAULT = ZPOOL_MM_RW -}; - bool zpool_has_pool(char *type); struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp); @@ -41,17 +21,19 @@ const char *zpool_get_type(struct zpool *pool); void zpool_destroy_pool(struct zpool *pool); -bool zpool_malloc_support_movable(struct zpool *pool); - int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp, unsigned long *handle); void zpool_free(struct zpool *pool, unsigned long handle); -void *zpool_map_handle(struct zpool *pool, unsigned long handle, - enum zpool_mapmode mm); +void *zpool_obj_read_begin(struct zpool *zpool, unsigned long handle, + void *local_copy); + +void zpool_obj_read_end(struct zpool *zpool, unsigned long handle, + void *handle_mem); -void zpool_unmap_handle(struct zpool *pool, unsigned long handle); +void zpool_obj_write(struct zpool *zpool, unsigned long handle, + void *handle_mem, size_t mem_len); u64 zpool_get_total_pages(struct zpool *pool); @@ -81,15 +63,16 @@ struct zpool_driver { void *(*create)(const char *name, gfp_t gfp); void (*destroy)(void *pool); - bool malloc_support_movable; int (*malloc)(void *pool, size_t size, gfp_t gfp, unsigned long *handle); void (*free)(void *pool, unsigned long handle); - bool sleep_mapped; - void *(*map)(void *pool, unsigned long handle, - enum zpool_mapmode mm); - void (*unmap)(void *pool, unsigned long handle); + void *(*obj_read_begin)(void *pool, unsigned long handle, + void *local_copy); + void (*obj_read_end)(void *pool, unsigned long handle, + void *handle_mem); + void (*obj_write)(void *pool, unsigned long handle, + void *handle_mem, size_t mem_len); u64 (*total_pages)(void *pool); }; diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index a48cd0ffe57d..c26baf9fb331 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -16,23 +16,6 @@ #include <linux/types.h> -/* - * zsmalloc mapping modes - * - * NOTE: These only make a difference when a mapped object spans pages. - */ -enum zs_mapmode { - ZS_MM_RW, /* normal read-write mapping */ - ZS_MM_RO, /* read-only (no copy-out at unmap time) */ - ZS_MM_WO /* write-only (no copy-in at map time) */ - /* - * NOTE: ZS_MM_WO should only be used for initializing new - * (uninitialized) allocations. Partial writes to already - * initialized allocations should use ZS_MM_RW to preserve the - * existing data. - */ -}; - struct zs_pool_stats { /* How many pages were migrated (freed) */ atomic_long_t pages_compacted; @@ -48,14 +31,18 @@ void zs_free(struct zs_pool *pool, unsigned long obj); size_t zs_huge_class_size(struct zs_pool *pool); -void *zs_map_object(struct zs_pool *pool, unsigned long handle, - enum zs_mapmode mm); -void zs_unmap_object(struct zs_pool *pool, unsigned long handle); - unsigned long zs_get_total_pages(struct zs_pool *pool); unsigned long zs_compact(struct zs_pool *pool); unsigned int zs_lookup_class_index(struct zs_pool *pool, unsigned int size); void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats); + +void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle, + void *local_copy); +void zs_obj_read_end(struct zs_pool *pool, unsigned long handle, + void *handle_mem); +void zs_obj_write(struct zs_pool *pool, unsigned long handle, + void *handle_mem, size_t mem_len); + #endif diff --git a/include/linux/zswap.h b/include/linux/zswap.h index d961ead91bf1..30c193a1207e 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -26,7 +26,7 @@ struct zswap_lruvec_state { unsigned long zswap_total_pages(void); bool zswap_store(struct folio *folio); -bool zswap_load(struct folio *folio); +int zswap_load(struct folio *folio); void zswap_invalidate(swp_entry_t swp); int zswap_swapon(int type, unsigned long nr_pages); void zswap_swapoff(int type); @@ -44,9 +44,9 @@ static inline bool zswap_store(struct folio *folio) return false; } -static inline bool zswap_load(struct folio *folio) +static inline int zswap_load(struct folio *folio) { - return false; + return -ENOENT; } static inline void zswap_invalidate(swp_entry_t swp) {} |